Attacks on AI Research AI security importance 50 1 min read In your stack
Is 4-Bit Quantization More Than Noise to a Chat Model's Safety Behaviour? Attributing Behavioural Shifts with Matched Perturbations
Study finds 4-bit quantization shifts refusal behaviour in Qwen2.5-3B and Llama-3.2-3B chat models, with one model complying with jailbreaks more often and the other less.
Techniques
Paper
Sources
arXiv (AI security papers) primary
Affects and mentions
Add any of these to your stack to follow them.
One-line summary and action are AI-assisted. Read the source before acting.