1 citations · 1 across the 12 of their papers we have counts for
7 papers · 1 filter
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…
Throttling Web Agents Using Reasoning Gates
Abhinav Kumar, Jaechul Roh, Ali Naseh +2
AI web agents use Internet resources at far greater speed, scale, and complexity -- changing how users and services interact. Deployed maliciously or erroneously, these agents coul…
Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
Anshuman Suri, Harsh Chaudhari, Yuefeng Peng +3
While poisoning attacks on machine learning models have been extensively studied, the mechanisms by which adversaries can distribute poisoned models at scale remain largely unexplo…
R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model
Ali Naseh, Harsh Chaudhari, Jaechul Roh +3
DeepSeek recently released R1, a high-performing large language model (LLM) optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performa…
OverThink: Slowdown Attacks on Reasoning LLMs
Abhinav Kumar, Jaechul Roh, Ali Naseh +4
A reasoning language model (RLM) generates costly reasoning tokens, often hidden from the users, that help it excel at many tasks. Our Overthink attack targets RLM-based applicatio…
Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
Ali Naseh, Yuefeng Peng, Anshuman Suri +3
Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to generate grounded responses by leveraging external knowledge databases without altering model parameter…
Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
Ali Naseh, Niloofar Mireshghallah
Recent work shows membership inference attacks (MIAs) on large language models (LLMs) produce inconclusive results, partly due to difficulties in creating non-member datasets witho…