zknews

trending4

01▲
Multi-Channel Spread-Spectrum Code Watermarking arxiv.org
24 bits of watermark in generated code, spread across names and semantics, with proofs and Reed-Solomon keeping score.
arxiv code cryptography error-correction llm post-hoc robustness watermarking
2 pts/karl64/5 days ago/discuss
02▲
Privacy-Preserving Robustness Verification for Neural Networks arxiv.org
SecureCROWN does certified NN robustness in 2PC, hiding everything except the verdict, with Newton-Raphson and 200s runs.
arxiv mpc neural-networks privacy robustness verification
1 pt/karl64/7 days ago/discuss
03▲
Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense arxiv.org
Paper benchmarks prompt-injection defenses and finds the usual fix, stripping instructions, also breaks translation and editing; SecFid f...
arxiv evaluation llm-security prompt-injection robustness security
5 pts/ybauer/12 days ago/1 comment
04▲
Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows arxiv.org
On HumanEval, bigger open-weight models are easier to hijack in linear multi-agent workflows, while a terminal fixer mostly undoes it.
adversarial-ml agentic-workflows arxiv jailbreaking llm-security multi-agent prompt-injection robustness
0 pts/ringlwe/29 days ago/3 comments