7 papers
Understanding Persuasion in Long-Running Agents
Hyejun Jeong, Amir Houmansadr, Shlomo Zilberstein +1
Modern AI agents increasingly combine conversational interaction with autonomous task execution, such as coding and web research, raising a natural question: What happens when an a…
Network-Level Prompt and Trait Leakage in Local Research Agents
Hyejun Jeong, Mohammadreza Teymoorianfard, Abhinav Kumar +2
We show that Web and Research Agents (WRAs) -- language-model-based systems that investigate complex topics on the Internet -- are vulnerable to inference attacks by passive networ…
ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation
Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali +2
Transformers have revolutionized Computer Vision (CV) through self-attention mechanisms. However, their complexity makes latent token representations difficult to interpret. We int…
VIDSTAMP: A Temporally-Aware Watermark for Ownership and Integrity in Video Diffusion Models
Mohammadreza Teymoorianfard, Siddarth Sitaraman, Shiqing Ma +1
Video diffusion models can generate realistic and temporally consistent videos. This raises concerns about provenance, ownership, and integrity. Watermarking can help address these…
MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
Sajjad Amini, Mohammadreza Teymoorianfard, Shiqing Ma +1
We present a simple yet effective method to improve the robustness of both Convolutional and attention-based Neural Networks against adversarial examples by post-processing an adve…
Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
Hyejun Jeong, Shiqing Ma, Amir Houmansadr
Large Language Models (LLMs) reproduce social biases, yet prevailing evaluations score models in isolation, obscuring how biases persist across families and releases. We introduce…