collaborators

13 papers

cs.CR2026

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…

cs.CR2026

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.…

cs.CV2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…