13 papers
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
Luze Sun, Anshuman Suri, Harsh Chaudhari +2
When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small number of crafted instruction…
Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
Harsh Chaudhari, Ethan Rathbun, Hanna Foerster +5
Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks.…
Identifying Models Behind Text-to-Image Leaderboards
Ali Naseh, Yuefeng Peng, Anshuman Suri +3
Text-to-image (T2I) models are increasingly popular, producing a large share of AI-generated images online. To compare model quality, voting-based leaderboards have become the stan…
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
Milad Nasr, Nicholas Carlini, Chawin Sitawarin +11
How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful…
Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
Ali Naseh, Anshuman Suri, Yuefeng Peng +3
Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is rank manipulation, where an atta…
Cascading Adversarial Bias from Injection to Distillation in Language Models
Harsh Chaudhari, Jamie Hayes, Matthew Jagielski +3
Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns abou…