#Research
All CosmicBytez Labs articles tagged #Research, across news, security advisories, how-to guides, and projects.
- News
New Tool Traces AI-Generated Videos Back to Their Source
Researchers from UC Riverside and Google DeepMind have developed SAGA, a multi-granular attribution tool that can identify which AI generator produced a...
- News
'Ghostcommit' Hides Prompt Injection in Images to Fool AI Agents and Steal Secrets
Security researchers have demonstrated 'Ghostcommit,' a technique that embeds prompt injection payloads inside PNG images to bypass AI code review tools...
- News
New TrojPix Attack Leaks Data From Air-Gapped Systems via Video Cable Emissions
Researchers at Shandong University have demonstrated TrojPix, a covert channel attack that exfiltrates data from air-gapped computers by manipulating...
- News
Leak Confirms OpenAI Is Testing a ChatGPT for Science Subscription
A leaked interface reveals OpenAI is developing a specialized ChatGPT subscription tier for scientific research, potentially offering tailored tools for...
- News
Security of 100 AI Agents Tested and Ranked – What You Need to Know
A new AI Risk Quadrant framework has benchmarked 100 AI agents across three dimensions: vulnerability to compromise, potential breach impact, and strength of…
- News
Making Vulnerable Drivers Exploitable Without Hardware: The
A new technical analysis reveals that many Windows kernel-mode drivers can be exploited from user mode without the physical hardware they were designed...
- News
ETH Zurich Finds 25 Password Recovery Attacks Against
Researchers from ETH Zurich demonstrated that the zero-knowledge encryption claims of major password managers break down if the server is compromised,...