RESEARCH 24
- LLMs Respond Differently to Harmful Prompts When AI Watermarking is Used
- Will AI Kill Us All Within The Next Decade?
- New GPUThor Attack Defeats NVIDIA ECC Protection for Root Access
- Researcher Tricks Apple's Find My into Sharing Location Data with Linux
- Call for Applications Information Controls Research Program 2026
- When Agentic Glue Melts Exploiting Cloudflare Code Mode and Workers
- Ransomware Moves up the Org Chart Managers Are Prime Targets
- GitHub-native Command-and-Control Framework OctoC2 Released
- No Single Pane of Glass Anatomy of an Azure Permission Takeover
- GitHub Copilot Sorry Dave, I can't do that harmful thing - unless you ask me in code
- Researchers Detail DifyTap Flaws in Dify That Could Expose AI Chats Across Tenants
- Bend the Beam Like Beckham to Defeat Anti-Jamming Tech
- Microsoft Backs Off Legal Threats Against Windows Security Researchers After BitLocker Backlash
- Researchers Built a Chatbot That Only Knows the World Before 1931
- Researchers Found Font-Rendering Trick to Hide Malicious Commands
- Twenty Years of Cloud Security Research
- Crypto-Funded Human Trafficking Is Exploding
- From Campus to C2 Tracking a Persistent Chinese Operation Against Vietnamese Universities
- Hackers Regularly Exploit Vulnerabilities Before Public Disclosure, Study Finds
- At last, a use case for AI agents with sky-high ROI Stealing crypto
- In the Wild Malware Prototype with Embedded Prompt Injection
- Fault Injection – Follow the White Rabbit
- Is b For Backdoor? Pre-Auth RCE Chain In Sitecore Experience Platform
- Twenty Years of Cloud Security Research