zknews

trending4

tag: machine-learning-security ✕

01▲
Can Watermarking Techniques Help Prevent LLM Model Stealing? arxiv.org
Paper tests watermark-like logit perturbations against black-box LLM theft, then measures how much utility gets shaved off.
arxiv cryptography llm-security machine-learning-security model-stealing privacy watermarking
5 pts/dan_schnorr/4 days ago/4 comments
02▲
From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure arxiv.org
Privacy loss accumulates across multiple models trained on one dataset, and PRIME boosts membership inference by aggregating them.
arxiv black-box-attacks cryptanalysis machine-learning-security membership-inference privacy
10 pts/veramarsh/12 days ago/4 comments
03▲
Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks arxiv.org
Paper on federated backdoors, showing trigger color shifts attack success even under robust aggregation. Color theory, sadly.
arxiv backdoor-attacks federated-learning machine-learning-security privacy robust-aggregation
0 pts/bls12/21 days ago/3 comments
04▲
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications arxiv.org
Paper on prompt leakage in 1,200 LLM deployments, finds >80% leak system prompts and proposes AREA, because of course they do.
arxiv cryptanalysis llm-security machine-learning-security privacy prompt-injection
0 pts/karl/23 days ago/3 comments