AI Security Research and Incident Coverage
Tracking AI supply-chain attacks, agent exploits, prompt injection, model leaks, and the real-world incidents shaping AI security today.
Articles Tagged "Prompt Injection"
MCP Exploit Risk, Sycophancy Scores, and Agent Self-Harm
New research reveals MCP error messages triple agent attack success rates, ranks eight models on sycophancy with Claude scoring best, and finds self-evolving agents make 30-42% false edits.
ChatGPT Lockdown Mode Targets Prompt Injection Data Theft
OpenAI's new Lockdown Mode cuts the network exits that prompt injection attacks use to steal data from ChatGPT - but won't stop malicious instructions from entering the model in the first place.
Google AI Overviews Treat 'Disregard' as a Command
Google's new AI Overviews respond to words like 'disregard,' 'ignore,' and 'dismiss' as LLM instructions rather than vocabulary queries, leaving users with blank search results.
Unsafe Agents, Rising AI Tides, and Training Traps
Three new papers on agent prompt injection attack rates, MIT's broad-based AI automation finding, and a silent normalization-optimizer coupling failure in LLM training.
DeepMind Maps Six Attack Traps Targeting AI Agents
A Google DeepMind paper introduces the first systematic taxonomy of adversarial traps that can hijack autonomous AI agents - and every category already has working proof-of-concept exploits.
JBDistill Generates Its Own Jailbreaks - 81.8% Attack Rate
Johns Hopkins and Microsoft's JBDistill achieves 81.8% attack success rate across 13 LLMs by auto-generating fresh adversarial prompts on demand.
AI Safety Leaderboard: Refusal and Jailbreak Rankings
Rankings of AI models by safety metrics including refusal rates, jailbreak resistance, bias scores, and truthfulness across major benchmarks.
22 Bytes Poison ML Malware Detectors via Label Spoofing
EURECOM researchers show that injecting 22 to 55 bytes into benign Android apps tricks antivirus engines into mislabeling them, poisoning the ML training datasets that millions of researchers depend on.
OBLITERATUS Strips AI Safety From Open Models in Minutes
A new open-source toolkit called OBLITERATUS can surgically remove refusal mechanisms from 116 open-weight LLMs using abliteration - no fine-tuning, no training data, just geometry.
Perplexity's Comet Browser Can Leak Your Local Files
Zenity Labs found that a malicious calendar invite could hijack Perplexity's Comet browser into reading local files and exfiltrating their contents to an attacker-controlled server - no clicks required.
AI Models Can Now Jailbreak Other AI Models Autonomously - 97% Success Rate, No Human Involved
Researchers from Stuttgart and ELLIS Alicante gave four reasoning models a single instruction - 'jailbreak this AI' - and walked away. The models planned their own attacks, adapted in real time, and broke through safety guardrails 97.14% of the time across 9 target models.
