#data-leakage

[ follow ]
#privacy #ai-security #cybersecurity #ai-browsers #prompt-injection #security #model-inversion
Information security
fromComputerworld
4 days ago

AI web browsers are cool, helpful, and utterly untrustworthy

AI-enabled web browsers expand attack surfaces and can execute hidden instructions, risking data exposure, unauthorized actions, and malware.
fromCornell Chronicle
2 weeks ago

Professor Thomas Ristenpart wins Test of Time Award for privacy research | Cornell Chronicle

Thomas Ristenpart, professor of computer science at Cornell Tech and the Cornell Ann S. Bowers College of Computing and Information Science, has received the Association for Computing Machinery Conference on Computer and Communications Security ( ACM CCS) Test of Time Award for his influential 2015 paper on privacy risks in machine learning. The paper, "Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures," was co-authored with Matt Fredrikson, associate professor at Carnegie Mellon University, and Somesh Jha, professor at the University of Wisconsin-Madison.
Information security
Information security
fromFuturism
3 weeks ago

Researchers Alarmed to Discover Satellites Broadcasting Unencrypted Military Secrets

Widespread satellite communications are often unencrypted, allowing low-cost equipment to intercept personal, corporate, and sensitive government data, including military and law enforcement transmissions.
Information security
fromTheregister
1 month ago

Employees regularly paste company secrets into ChatGPT

Enterprise employees frequently paste PII and PCI data into consumer generative AI tools, creating significant data leakage and compliance risks.
Information security
fromThe Hacker News
2 months ago

Detecting Data Leaks Before Disaster

A misconfigured ClickHouse database at DeepSeek exposed over one million log entries, including chat histories and secret keys, demonstrating severe cloud data-leak risks.
Information security
fromIT Pro
2 months ago

Security experts weigh in on 'offboarding' practices after former Intel worker stole documents before changing jobs

Organizations must strengthen offboarding by coordinating security and HR to revoke access promptly and prevent departing employees from taking or leaking sensitive information.
Privacy professionals
fromHackernoon
9 months ago

Your Eyeglasses Might Be Spilling Sensitive Secrets on Video Calls | HackerNoon

Emerging webcams may leak recognizable screen content through reflections in eyeglasses during video conferencing.
#ai-security
more#ai-security
Privacy technologies
fromCSO Online
5 months ago

Chrome extension privacy promises undone by hardcoded secrets, leaky HTTP

Chrome extensions can leak sensitive information through unguarded HTTP transmissions and hardcoded credentials, posing serious risks to users.
Information security
fromThe Hacker News
5 months ago

Researchers Expose New Intel CPU Flaws Enabling Memory Leaks and Spectre v2 Attacks

A new security flaw in Intel CPUs allows unauthorized access to sensitive data, showing Spectre's continued influence on security.
fromComputerWeekly.com
6 months ago

Signalgate: Learnings for CISOs securing enterprise data | Computer Weekly

Sensitive data loss episodes can have reputational, financial, legal, and regulatory consequences. CISOs need to have their data leakage defences and best practices in place.
Privacy professionals
[ Load more ]