2 citations · 2 across the 8 of their papers we have counts for
9 papers
AttenMIA: LLM Membership Inference Attack through Attention Signals
Pedram Zaree, Md Abdullah Al Mamun, Yue Dong +2
Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency…
A Trajectory-free Crash Detection Framework with Generative Approach and Segment Map Diffusion
Weiying Shen, Hao Yu, Yu Dong +3
Real-time crash detection is essential for developing proactive safety management strategy and enhancing overall traffic efficiency. To address the limitations associated with traj…
Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
Erfan Shayegani, Keegan Hines, Yue Dong +6
Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Bl…
What Do They Fix? LLM-Aided Categorization of Security Patches for Critical Memory Bugs
Xingyu Li, Juefei Pu, Yifan Wu +11
Open-source software projects are foundational to modern software ecosystems, with the Linux kernel standing out as a critical exemplar due to its ubiquity and complexity. Although…
Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
Erfan Shayegani, G M Shahariar, Sara Abdali +3
Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant…
Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
Pedram Zaree, Md Abdullah Al Mamun, Quazi Mishkatul Alam +3
Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is impo…
Mitigating Extrinsic Gender Bias for Bangla Classification Tasks
Sajib Kumar Saha Joy, Arman Hassan Mahy, Meherin Sultana +4
In this study, we investigate extrinsic gender bias in Bangla pretrained language models, a largely underexplored area in low-resource languages. To assess this bias, we construct…
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
Saketh Bachu, Erfan Shayegani, Rohit Lal +6
Vision-language models (VLMs) have improved significantly in their capabilities, but their complex architecture makes their safety alignment challenging. In this paper, we reveal a…
Cross-Modal Safety Alignment: Is textual unlearning all you need?
Trishna Chakraborty, Erfan Shayegani, Zikui Cai +5
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing…