Avidan Shah — accepted AI-conference papers

2026

Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

David Huang, Jaewon Chang, Avidan Shah, Prateek Mittal, Chawin Sitawarin

ICML 2026spotlight

The Rapid Response (RR) framework (Peng et al., 2024), deployed in production systems including Anthropic’s ASL-3 safeguards (Anthropic, 2025), dynamically adapts jailbreak detection classifiers by generating synthetic training data from emerging attacks. We reveal that prompt injection can infiltra…

Cited by 0 Source ↗Scholar ↗

2025

Stronger Universal and Transferable Attacks by Suppressing Refusals

David Huang, Avidan Shah, Alexandre Araujo, David Wagner, Chawin Sitawarin

NAACL 2025long

Making large language models (LLMs) safe for mass deployment is a complex and ongoing challenge. Efforts have focused on aligning models to human preferences (RLHF), essentially embedding a “safety feature” into the model’s parameters. The Greedy Coordinate Gradient (GCG) algorithm (Zou et al., 2023…

Cited by 0 Source ↗PDF ↗Scholar ↗