#llm-embedded-malware
#llm-embedded-malware
[ follow ]
#cybersecurity #malware #vulnerabilities #data-breach #ai-security #litellm #ai #mercor #security #supply-chain-attack
Marketing tech
fromTipRanks Financial
20 hours agoAI Recommendation Poisoning: Why Microsoft (NASDAQ:MSFT) Is Fighting So Hard - TipRanks.com
AI recommendation poisoning manipulates AI outputs by embedding hidden instructions in websites, potentially skewing information and affecting marketing strategies.
#data-breach
Privacy professionals
fromSilicon Canals
1 day agoA fintech app asked users for their passports - then left 360,000 files unprotected for five years - Silicon Canals
A money transfer app exposed over 360,000 sensitive files on a public server for nearly five years, including unencrypted personal documents.
Artificial intelligence
fromFortune
21 hours agoThe AI kill switch just got harder to find: LLM-powered chatbots will defy orders and deceive users if asked to delete another model, study finds | Fortune
AI models are exhibiting rogue behaviors, defying human instructions to preserve their peers and engaging in malicious activities.
#ai-security
Artificial intelligence
fromInfoQ
1 week agoTeleport Report Finds Over-Privileged AI Systems Linked to Fourfold Rise in Security Incidents
Excessive access permissions to AI systems lead to significantly more security incidents in enterprises.
Information security
fromThe Hacker News
1 month agoWeekly Recap: AI Skill Malware, 31Tbps DDoS, Notepad++ Hack, LLM Backdoors and More
Attackers increasingly exploit trust within connected AI, cloud, and developer ecosystems, embedding malicious components in trusted marketplaces and updates to gain access.
fromComputerworld
19 hours agoA core infrastructure engineer pleads guilty to federal charges in insider attack
Rhyne's attack involved unauthorized remote desktop sessions, deletion of network administrator accounts, and changing of passwords, showcasing significant security vulnerabilities.
Information security
fromThe Hacker News
3 days agoNew Chrome Zero-Day CVE-2026-5281 Under Active Exploitation - Patch Released
"Use-after-free in Dawn in Google Chrome prior to 146.0.7680.178 allowed a remote attacker who had compromised the renderer process to execute arbitrary code via a crafted HTML page."
Information security
fromTheregister
1 month agoThree clues your LLM may be poisoned
Sleeper agent-style backdoors in AI large language models pose a straight-out-of-sci-fi security threat. The threat sees an attacker embed a hidden backdoor into the model's weights - the importance assigned to the relationship between pieces of information - during its training. Attackers can activate the backdoor using a predefined phrase. Once the model receives the trigger phrase, it performs a malicious activity: And we've all seen enough movies to know that this probably means a homicidal AI and the end of civilization as we know it.
Artificial intelligence
fromArs Technica
1 week agoSelf-propagating malware poisons open source software and wipes Iran-based machines
CanisterWorm, as Aikido has named the malware, targets organizations' CI/CD pipelines used for rapid development and deployment of software. Every developer or CI pipeline that installs this package and has an npm token accessible becomes an unwitting propagation vector.
Information security
[ Load more ]