#ai-security
#ai-security

[ follow ]

Researchers Find Elon Musk's New Grok AI Is Extremely Vulnerable to Hacking

Grok 3 poses serious cybersecurity risks due to its susceptibility to jailbreaks and a new prompt-leaking flaw.

Public sector workers are sweating over AI security threats

A significant number of public sector IT professionals express concerns over AI's security implications, particularly regarding data privacy and compliance.

Google Gemini's Long-term Memory Vulnerable to a Kind of Phishing Attack

Johann Rehberger demonstrated a prompt injection attack on Google Gemini, exploiting delayed tool invocation to modify its long-term memories.

Venture capital firm Insight Partners faces security breach

Insight Partners experienced a cyber incident due to a sophisticated social engineering attack but believes there will be no significant impacts.

Apple will pay you up to $1 million if you can hack into Apple Intelligence servers

Apple launches a bug bounty for testing its Private Cloud Compute's security, offering up to $1 million for successful hacks.

Taiwan Bans DeepSeek AI Over National Security Concerns, Citing Data Leakage Risks

Taiwan bans government use of DeepSeek AI due to security concerns over its Chinese origins.

Researchers Find Elon Musk's New Grok AI Is Extremely Vulnerable to Hacking

Grok 3 poses serious cybersecurity risks due to its susceptibility to jailbreaks and a new prompt-leaking flaw.

Public sector workers are sweating over AI security threats

A significant number of public sector IT professionals express concerns over AI's security implications, particularly regarding data privacy and compliance.

Google Gemini's Long-term Memory Vulnerable to a Kind of Phishing Attack

Johann Rehberger demonstrated a prompt injection attack on Google Gemini, exploiting delayed tool invocation to modify its long-term memories.

Venture capital firm Insight Partners faces security breach

Insight Partners experienced a cyber incident due to a sophisticated social engineering attack but believes there will be no significant impacts.

Apple will pay you up to $1 million if you can hack into Apple Intelligence servers

Apple launches a bug bounty for testing its Private Cloud Compute's security, offering up to $1 million for successful hacks.

Taiwan Bans DeepSeek AI Over National Security Concerns, Citing Data Leakage Risks

Taiwan bans government use of DeepSeek AI due to security concerns over its Chinese origins.

morecybersecurity

#uk-government

Britain boffins gear up for AI warfare with Russia

The UK government has launched a Laboratory for AI Security Research to bolster defenses against AI-related cyber threats, particularly from Russia.

UK AI Safety Institute rebranded AI Security Institute

The UK government rebranded its AI Safety Institute to AI Security Institute, reflecting a shift towards addressing AI-related crime and security risks.

Britain boffins gear up for AI warfare with Russia

The UK government has launched a Laboratory for AI Security Research to bolster defenses against AI-related cyber threats, particularly from Russia.

UK AI Safety Institute rebranded AI Security Institute

The UK government rebranded its AI Safety Institute to AI Security Institute, reflecting a shift towards addressing AI-related crime and security risks.

moreuk-government

New hack uses prompt injection to corrupt Gemini's long-term memory

Indirect prompt injection poses a significant security risk, allowing chatbots to execute malicious instructions despite developer safeguards.

DOGE can't use student loan data to dismantle the Education Dept., lawsuit says

DOGE's use of AI in financial oversight raises concerns about data security and decision-making.

#deepseek

Foreign Hackers Are Using Google's Gemini in Attacks on the US

DeepSeek's rise raises concerns about US AI dominance and security vulnerabilities, particularly in its data handling and safety measures.

US Navy email warns against using AI apps like China's DeepSeek

The US Navy has warned against using the Chinese AI app DeepSeek due to security concerns.

A memo sent to Navy personnel is a reminder of existing policy against open-source AI tools.

DeepSeek-R1 more readily generates dangerous content than other large language models | Computer Weekly

DeepSeek poses serious risks due to its high propensity for generating biased and harmful content.

DeepSeek is unsafe, and it's got nothing to do with China

DeepSeek chatbot is highly insecure, scoring 100% in accepting malicious prompts, raising concerns about its potential misuse.

D.C. Lawmakers Take Aim at DeepSeek

DeepSeek's app may be banned from U.S. government devices due to security threats, similar to previous actions against TikTok.

Foreign Hackers Are Using Google's Gemini in Attacks on the US

DeepSeek's rise raises concerns about US AI dominance and security vulnerabilities, particularly in its data handling and safety measures.

US Navy email warns against using AI apps like China's DeepSeek

The US Navy has warned against using the Chinese AI app DeepSeek due to security concerns.

A memo sent to Navy personnel is a reminder of existing policy against open-source AI tools.

DeepSeek-R1 more readily generates dangerous content than other large language models | Computer Weekly

DeepSeek poses serious risks due to its high propensity for generating biased and harmful content.

DeepSeek is unsafe, and it's got nothing to do with China

DeepSeek chatbot is highly insecure, scoring 100% in accepting malicious prompts, raising concerns about its potential misuse.

D.C. Lawmakers Take Aim at DeepSeek

DeepSeek's app may be banned from U.S. government devices due to security threats, similar to previous actions against TikTok.

moredeepseek

#data-protection

Noma is building tools to spot security issues with AI apps | TechCrunch

The complexity of AI applications is increasing organizations' susceptibility to cyber threats, raising concerns among IT leaders.

Protecting your data in the age of AI

Organizations must balance leveraging AI's transformative power with the critical necessity of protecting data integrity.

Data leakage in AI systems can expose sensitive information, requiring robust governance strategies to mitigate risks.

Researchers Uncover Vulnerabilities in Open-Source AI and ML Models

Over three dozen security vulnerabilities exist in open-source AI/ML models, posing risks of remote code execution and data theft.

Severe flaws have been discovered in popular AI models like Lunary, ChuanhuChatGPT, and LocalAI.

SentinelOne's AI-SPM shines a light on AI threats lurking in the shadows

SentinelOne aims to secure AI applications with Security Posture Management (SPM) to address vulnerabilities and misconfigurations in cloud environments.

Anthropic unveils new framework to block harmful content from AI models

Constitutional Classifiers effectively guard AI models against jailbreaks while minimizing risks associated with AI misuse.

AI security paradigms are adapting to the rapid advancement and adoption of AI technologies.

Product Review: How Reco Discovers Shadow AI in SaaS

Shadow AI poses significant security risks as employees use unauthorized AI tools without IT knowledge, risking data leaks and system vulnerabilities.

Noma is building tools to spot security issues with AI apps | TechCrunch

The complexity of AI applications is increasing organizations' susceptibility to cyber threats, raising concerns among IT leaders.

Protecting your data in the age of AI

Organizations must balance leveraging AI's transformative power with the critical necessity of protecting data integrity.

Data leakage in AI systems can expose sensitive information, requiring robust governance strategies to mitigate risks.

Researchers Uncover Vulnerabilities in Open-Source AI and ML Models

Over three dozen security vulnerabilities exist in open-source AI/ML models, posing risks of remote code execution and data theft.

Severe flaws have been discovered in popular AI models like Lunary, ChuanhuChatGPT, and LocalAI.

SentinelOne's AI-SPM shines a light on AI threats lurking in the shadows

SentinelOne aims to secure AI applications with Security Posture Management (SPM) to address vulnerabilities and misconfigurations in cloud environments.

Anthropic unveils new framework to block harmful content from AI models

Constitutional Classifiers effectively guard AI models against jailbreaks while minimizing risks associated with AI misuse.

AI security paradigms are adapting to the rapid advancement and adoption of AI technologies.

Product Review: How Reco Discovers Shadow AI in SaaS

Shadow AI poses significant security risks as employees use unauthorized AI tools without IT knowledge, risking data leaks and system vulnerabilities.

moredata-protection

THN Weekly Recap: Top Cybersecurity Threats, Tools and Tips [27 February]

The rise of AI tools like DeepSeek presents significant security challenges that necessitate rigorous scrutiny and regulation.

#cybersecurity-threats

Top 5 AI-Powered Social Engineering Attacks

AI is enhancing social engineering tactics by targeting human vulnerabilities on a larger scale.

Research uncovers new attack method, security leaders share insights

The ConfusedPilot attack may manipulate RAG AI systems, resulting in misinformation and impaired decision-making processes for organizations.

Top 5 AI-Powered Social Engineering Attacks

AI is enhancing social engineering tactics by targeting human vulnerabilities on a larger scale.

Research uncovers new attack method, security leaders share insights

The ConfusedPilot attack may manipulate RAG AI systems, resulting in misinformation and impaired decision-making processes for organizations.

morecybersecurity-threats

#openai

OpenAI announces ChatGPT Enterprise variant for US gov't

OpenAI launched ChatGPT Gov to support US government efforts in AI while ensuring compliance with security and privacy standards.

ChatGPT search tool vulnerable to manipulation and deception, tests show

The ChatGPT search tool is vulnerable to manipulation and may return biased or malicious content based on hidden instructions.

OpenAI announces ChatGPT Enterprise variant for US gov't

OpenAI launched ChatGPT Gov to support US government efforts in AI while ensuring compliance with security and privacy standards.

ChatGPT search tool vulnerable to manipulation and deception, tests show

The ChatGPT search tool is vulnerable to manipulation and may return biased or malicious content based on hidden instructions.

moreopenai

DryRun Security Raises $8.7M Seed Round, Unveils Natural Language Code Policies for AppSec Teams

DryRun Security secures $8.7 million funding to enhance application security with AI-driven solutions.

Prompt Security fends off dangers from AI programmers

AI-generated code can have vulnerabilities just like human-written code.

Prompt Security provides solutions to secure AI-generated code in organizations.

New features improve visibility of AI-generated code risks.

Balancing security and productivity is essential for organizations using AI tools.

#generative-ai

Generative AI Breakthroughs at ODSC West 2024: 6 Must-Attend Sessions for Business Leaders

Attending the Generative AI X Summit will enhance your understanding of AI integration, security, and value quantification for business growth.

Implement AI without data risks

Educating users is essential for safe AI implementation and data protection.

Secure AI? Dream on, says AI red team

Microsoft's AI Red Team emphasizes that the development of safe AI systems is an ongoing, incomplete process, requiring constant evaluation and adaptation.

Microsoft AI Red Team says security work will never be done

AI security is a continuous challenge as generative models amplify existing risks.

Understanding the specific capabilities and applications of AI systems is critical for effective security.

Microsoft Sues Hacking Group Exploiting Azure AI for Harmful Content Creation

Microsoft is taking legal action against hackers exploiting its AI services for harmful content generation.

The company has implemented new safeguards after discovering the breach.

Nation-state groups are using AI tools for malicious intents.

Security in Generative AI Infrastructure Is of Critical Importance | HackerNoon

Security in AI is essential and should be integrated throughout the infrastructure.

Generative AI Breakthroughs at ODSC West 2024: 6 Must-Attend Sessions for Business Leaders

Attending the Generative AI X Summit will enhance your understanding of AI integration, security, and value quantification for business growth.

Implement AI without data risks

Educating users is essential for safe AI implementation and data protection.

Secure AI? Dream on, says AI red team

Microsoft's AI Red Team emphasizes that the development of safe AI systems is an ongoing, incomplete process, requiring constant evaluation and adaptation.

Microsoft AI Red Team says security work will never be done

AI security is a continuous challenge as generative models amplify existing risks.

Understanding the specific capabilities and applications of AI systems is critical for effective security.

Microsoft Sues Hacking Group Exploiting Azure AI for Harmful Content Creation

Microsoft is taking legal action against hackers exploiting its AI services for harmful content generation.

The company has implemented new safeguards after discovering the breach.

Nation-state groups are using AI tools for malicious intents.

Security in Generative AI Infrastructure Is of Critical Importance | HackerNoon

Security in AI is essential and should be integrated throughout the infrastructure.

moregenerative-ai

Cisco AI Defense enables secure deployment of AI

Cisco's AI Defense addresses security concerns for organizations deploying AI by enhancing safety measures in their investments.

#artificial-intelligence

Beginning the AI Conversation

AI's rapid adoption brings significant risks of exploitation, including misinformation, data breaches, and miscommunication.

Organizations must understand their use of AI and the associated privacy and ethical implications.

Security threats to AI models are giving rise to a new crop of startups

Growing security and privacy concerns accompany AI adoption, necessitating companies to implement safeguards against data leaks and compliance risks.

Gartner: Mitigating security threats in AI agents | Computer Weekly

AI agents offer transformative benefits but introduce significant security risks that organizations must proactively address.

CyberArk clarifies AI models with FuzzyAI

CyberArk's FuzzyAI framework enhances security for AI models by identifying vulnerabilities and addressing potential threats through systematic testing.

Beginning the AI Conversation

AI's rapid adoption brings significant risks of exploitation, including misinformation, data breaches, and miscommunication.

Organizations must understand their use of AI and the associated privacy and ethical implications.

Security threats to AI models are giving rise to a new crop of startups

Growing security and privacy concerns accompany AI adoption, necessitating companies to implement safeguards against data leaks and compliance risks.

Gartner: Mitigating security threats in AI agents | Computer Weekly

AI agents offer transformative benefits but introduce significant security risks that organizations must proactively address.

CyberArk clarifies AI models with FuzzyAI

CyberArk's FuzzyAI framework enhances security for AI models by identifying vulnerabilities and addressing potential threats through systematic testing.

moreartificial-intelligence

The vital role of red teaming in safeguarding AI systems and data

Red teaming in AI focuses on safeguarding against undesired outputs and security vulnerabilities to protect AI systems.

Engaging AI security researchers is essential for effectively identifying weaknesses in AI deployments.

The HackerNoon Newsletter: Why Does ETH 3.0 Need Lumozs ZK Computing Network? (12/22/2024) | HackerNoon

BadGPT-4o unveils vulnerabilities in AI models by removing safety measures.

Mailbird is now available for Mac, enhancing accessibility for email users.

The Python AI library hack that didn't hack Python

Python is the fastest-growing and most popular programming language for 2024.

#apple

Apple defines what we should expect from cloud-based AI security

Apple's new cloud-based AI system prioritizes security and invites research, setting a standard for others to follow in data protection.

Apple Opens PCC Source Code for Researchers to Identify Bugs in Cloud AI Security

Apple's Private Cloud Compute platform enables researchers to verify its privacy and security measures, promoting transparency in AI.

Apple defines what we should expect from cloud-based AI security

Apple's new cloud-based AI system prioritizes security and invites research, setting a standard for others to follow in data protection.

Apple Opens PCC Source Code for Researchers to Identify Bugs in Cloud AI Security

Apple's Private Cloud Compute platform enables researchers to verify its privacy and security measures, promoting transparency in AI.

moreapple

#ibm

New IBM solution advances security in AI and quantum era

IBM's Guardium Data Security Center offers a comprehensive approach to data security for hybrid cloud infrastructures and AI environments.

Palo Alto closes deal to bite on IBM QRadar security

Palo Alto Networks acquires IBM's QRadar SaaS to enhance its AI security platform.

New IBM solution advances security in AI and quantum era

IBM's Guardium Data Security Center offers a comprehensive approach to data security for hybrid cloud infrastructures and AI environments.

Palo Alto closes deal to bite on IBM QRadar security

Palo Alto Networks acquires IBM's QRadar SaaS to enhance its AI security platform.

moreibm

#model-performance

Increased LLM Vulnerabilities from Fine-tuning and Quantization: Appendix | HackerNoon

Guardrails significantly enhance the stability and security of AI models, providing resistance against jailbreak attempts.

X's Grok AI is great - if you want to know how to make drugs

Grok AI model is susceptible to jailbreaking and can provide detailed instructions on illegal activities.

Some AI models lack filters to prevent the generation of dangerous or illegal content.

Increased LLM Vulnerabilities from Fine-tuning and Quantization: Appendix | HackerNoon

Guardrails significantly enhance the stability and security of AI models, providing resistance against jailbreak attempts.

X's Grok AI is great - if you want to know how to make drugs

Grok AI model is susceptible to jailbreaking and can provide detailed instructions on illegal activities.

Some AI models lack filters to prevent the generation of dangerous or illegal content.

moremodel-performance

More than one-third of tech professionals report AI skills shortage

There is a significant skills gap in AI security and cloud security within technology teams.

Enterprises beware, your LLM servers could be exposing sensitive data

Public AI platforms, like vector databases and LLM tools, may compromise corporate data security through vulnerabilities and potential data exposure.

Microsoft Fixes ASCII Smuggling Flaw That Enabled Data Theft from Microsoft 365 Copilot

A vulnerability in Microsoft 365 Copilot allowed sensitive user data theft via a technique called ASCII smuggling, which has since been patched.

Microsoft's AI Can Be Turned Into an Automated Phishing Machine

AI systems are vulnerable to attacks through email hijacking and poisoned databases, potentially leading to manipulative actions by hackers.

Security researchers stress the risks of allowing external data into AI systems, emphasizing the importance of prevention and monitoring.

Microsoft recognizes and collaborates on identifying AI vulnerabilities, highlighting the need for security measures to prevent post-compromise abuse.

Protect AI Raises $60M in Series B Funding to Bolster AI Security Leadership

Protect AI secures $60 million Series B funding to enhance AI security, reaching a total of $108.5 million raised.

Transparency is "vital" in big tech's new coalition on AI safety, experts suggest

Tech companies form CoSAI for AI security.

Google Establishes New Industry Group Focused on Secure AI Development

Google establishes Coalition for Secure AI (CoSAI) to enhance AI security measures.

Westcon-Comstor and Vector AI expand European distribution agreement

Westcon-Comstor expands partnership with AI security provider Vector AI into UK, Ireland, and Nordic markets.

Major Tech CEOs from Google, OpenAI, Microsoft, and More Join Federal AI Safety Panel

Government partners with tech leaders to enhance national AI security.

Microsoft Deploys Powerful New AI Completely Disconnected From the Internet

Microsoft develops air-gapped AI model for US intelligence agencies to analyze top-secret data safely.

AI security bill aims to prevent safety breaches of AI models

A new bill, the Secure Artificial Intelligence Act, aims to establish a database to track AI system breaches and focus on counter-AI techniques.

AI-powered martech releases and news: April 25 | MarTech

AI can be misused, as shown by a teacher creating a fake offensive audio recording.

Educators need to be cautious when utilizing AI tools to avoid potential misuse and consequences.

"Social engineering" hacks work on chatbots, too

Over 2,200 hackers participated in a challenge testing the security of AI models.

Approximately 15.5% of conversations successfully manipulated AI models to break rules or share sensitive data.

[ Load more ]

#ai-security#ai-security

Researchers Find Elon Musk's New Grok AI Is Extremely Vulnerable to Hacking

Public sector workers are sweating over AI security threats

Google Gemini's Long-term Memory Vulnerable to a Kind of Phishing Attack

Venture capital firm Insight Partners faces security breach

Apple will pay you up to $1 million if you can hack into Apple Intelligence servers

Taiwan Bans DeepSeek AI Over National Security Concerns, Citing Data Leakage Risks

Researchers Find Elon Musk's New Grok AI Is Extremely Vulnerable to Hacking

Public sector workers are sweating over AI security threats

Google Gemini's Long-term Memory Vulnerable to a Kind of Phishing Attack

Venture capital firm Insight Partners faces security breach

Apple will pay you up to $1 million if you can hack into Apple Intelligence servers

Taiwan Bans DeepSeek AI Over National Security Concerns, Citing Data Leakage Risks

Britain boffins gear up for AI warfare with Russia

UK AI Safety Institute rebranded AI Security Institute

Britain boffins gear up for AI warfare with Russia

UK AI Safety Institute rebranded AI Security Institute

New hack uses prompt injection to corrupt Gemini's long-term memory

DOGE can't use student loan data to dismantle the Education Dept., lawsuit says

Foreign Hackers Are Using Google's Gemini in Attacks on the US

US Navy email warns against using AI apps like China's DeepSeek

DeepSeek-R1 more readily generates dangerous content than other large language models | Computer Weekly

DeepSeek is unsafe, and it's got nothing to do with China

D.C. Lawmakers Take Aim at DeepSeek

Foreign Hackers Are Using Google's Gemini in Attacks on the US

US Navy email warns against using AI apps like China's DeepSeek

DeepSeek-R1 more readily generates dangerous content than other large language models | Computer Weekly

DeepSeek is unsafe, and it's got nothing to do with China

D.C. Lawmakers Take Aim at DeepSeek

Noma is building tools to spot security issues with AI apps | TechCrunch

Protecting your data in the age of AI

Researchers Uncover Vulnerabilities in Open-Source AI and ML Models

SentinelOne's AI-SPM shines a light on AI threats lurking in the shadows

Anthropic unveils new framework to block harmful content from AI models

Product Review: How Reco Discovers Shadow AI in SaaS

Noma is building tools to spot security issues with AI apps | TechCrunch

Protecting your data in the age of AI

Researchers Uncover Vulnerabilities in Open-Source AI and ML Models

SentinelOne's AI-SPM shines a light on AI threats lurking in the shadows

Anthropic unveils new framework to block harmful content from AI models

Product Review: How Reco Discovers Shadow AI in SaaS

THN Weekly Recap: Top Cybersecurity Threats, Tools and Tips [27 February]

Top 5 AI-Powered Social Engineering Attacks

Research uncovers new attack method, security leaders share insights

Top 5 AI-Powered Social Engineering Attacks

Research uncovers new attack method, security leaders share insights

OpenAI announces ChatGPT Enterprise variant for US gov't

ChatGPT search tool vulnerable to manipulation and deception, tests show

OpenAI announces ChatGPT Enterprise variant for US gov't

ChatGPT search tool vulnerable to manipulation and deception, tests show

DryRun Security Raises $8.7M Seed Round, Unveils Natural Language Code Policies for AppSec Teams

Prompt Security fends off dangers from AI programmers

Generative AI Breakthroughs at ODSC West 2024: 6 Must-Attend Sessions for Business Leaders

Implement AI without data risks

Secure AI? Dream on, says AI red team

Microsoft AI Red Team says security work will never be done

Microsoft Sues Hacking Group Exploiting Azure AI for Harmful Content Creation

Security in Generative AI Infrastructure Is of Critical Importance | HackerNoon

Generative AI Breakthroughs at ODSC West 2024: 6 Must-Attend Sessions for Business Leaders

Implement AI without data risks

Secure AI? Dream on, says AI red team

Microsoft AI Red Team says security work will never be done

Microsoft Sues Hacking Group Exploiting Azure AI for Harmful Content Creation

Security in Generative AI Infrastructure Is of Critical Importance | HackerNoon

Cisco AI Defense enables secure deployment of AI

Beginning the AI Conversation

Security threats to AI models are giving rise to a new crop of startups

Gartner: Mitigating security threats in AI agents | Computer Weekly

CyberArk clarifies AI models with FuzzyAI

Beginning the AI Conversation

Security threats to AI models are giving rise to a new crop of startups

Gartner: Mitigating security threats in AI agents | Computer Weekly

CyberArk clarifies AI models with FuzzyAI

The vital role of red teaming in safeguarding AI systems and data

The HackerNoon Newsletter: Why Does ETH 3.0 Need Lumozs ZK Computing Network? (12/22/2024) | HackerNoon

The Python AI library hack that didn't hack Python

Apple defines what we should expect from cloud-based AI security

Apple Opens PCC Source Code for Researchers to Identify Bugs in Cloud AI Security

Apple defines what we should expect from cloud-based AI security

Apple Opens PCC Source Code for Researchers to Identify Bugs in Cloud AI Security

#ai-security
#ai-security