Paper says RAG poison filters rely on construction shortcuts, not content
Stripping PoisonedRAG's question prefix drops reimplemented RAGuard from AUROC 0.953 to 0.758 and raises its miss rate to 0.763.
Stories per day · 30 days
2 RSS
6 stories, newest first · one card per story
Stories tagged #defenses
Towards Safe World Models: Risks, Defenses, and Evaluation
A survey maps world-model safety risks, defenses, and evaluation across six lifecycle stages using 163 works.
pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation
Tencent's pikit toolkit benchmarks indirect prompt injection attacks, channels, and defenses for LLM coding agents.
Distillation Defenses Easily Break After Reinforcement Learning
Distillation defenses for closed language models often fail after later reinforcement learning.
Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?
A systematic study shows input-level adversarial defenses provide inconsistent, often near-zero protection against observation-level attacks on video LLMs.
Understanding the Privacy-Preserving Potential of HTTP/2 Against Webpage Fingerprinting
Researchers show HTTP/2 features can emulate website fingerprinting defenses like FRONT and Tamaraw with tunable privacy-overhead trade-offs.