Erfan Shayegani

16 papers A* 3Journal 11Unranked 2
YearRankTypeTitle / Venue / Authors
2025 J jnl
Evil Vizier: Vulnerabilities of LLM-Integrated XR Systems.
CoRR
Yicheng Zhang, Zijian Huang, Sophie Chen, Erfan Shayegani, Jiasi Chen, Nael B. Abu-Ghazaleh
2025 J jnl
From Measurement to Expertise: Empathetic Expert Adapters for Context-Based Empathy in Conversational AI Agents.
CoRR
Erfan Shayegani, Jina Suh, Andy Wilson, Nagu Rangan, Javier Hernandez
2025 J jnl
Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness.
CoRR
Erfan Shayegani, Keegan Hines, Yue Dong, Nael B. Abu-Ghazaleh, Roman Lutz, Spencer Whitehead, Vidhisha Balachandran, Besmira Nushi, Vibhav Vineet
2025 A* conf
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models.
ICML
Saketh Bachu, Erfan Shayegani, Rohit Lal, Trishna Chakraborty, Arindam Dutta, Chengyu Song, Yue Dong, Nael B. Abu-Ghazaleh, Amit Roy-Chowdhury
2025 J jnl
Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots.
CoRR
Erfan Shayegani, G. M. Shahariar, Sara Abdali, Lei Yu, Nael B. Abu-Ghazaleh, Yue Dong
2025 J jnl
Modeling Hierarchical Thinking in Large Reasoning Models.
CoRR
G. M. Shahariar, Ali Nazari, Erfan Shayegani, Nael B. Abu-Ghazaleh
2025 J jnl
SENSE-7: Taxonomy and Dataset for Measuring User Perceptions of Empathy in Sustained Human-AI Conversations.
CoRR
Jina Suh, Lindy Le, Erfan Shayegani, Gonzalo A. Ramos, Judith Amores, Desmond C. Ong, Mary Czerwinski, Javier Hernandez
2024 — conf
Can Textual Unlearning Solve Cross-Modality Safety Alignment?
EMNLP (Findings)
Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael B. Abu-Ghazaleh, M. Salman Asif, Yue Dong, Amit K. Roy-Chowdhury, Chengyu Song
2024 J jnl
Cross-Modal Safety Alignment: Is textual unlearning all you need?
CoRR
Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael B. Abu-Ghazaleh, M. Salman Asif, Yue Dong, Amit K. Roy-Chowdhury, Chengyu Song
2024 A* conf
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models.
ICLR
Erfan Shayegani, Yue Dong, Nael B. Abu-Ghazaleh
2024 — conf
Securing Shared State in Multi-User Augmented Reality.
ISMAR-Adjunct
Jiasi Chen, Carter Slocum, Yicheng Zhang, Erfan Shayegani, Pedram Zaree, Nael B. Abu-Ghazaleh
2024 A* conf
That Doesn't Go There: Attacks on Shared State in Multi-User Augmented Reality Applications.
USENIX Security Symposium
Carter Slocum, Yicheng Zhang, Erfan Shayegani, Pedram Zaree, Nael B. Abu-Ghazaleh, Jiasi Chen
2024 J jnl
Unfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models.
CoRR
Saketh Bachu, Erfan Shayegani, Trishna Chakraborty, Rohit Lal, Arindam Dutta, Chengyu Song, Yue Dong, Nael B. Abu-Ghazaleh, Amit K. Roy-Chowdhury
2023 J jnl
Plug and Pray: Exploiting off-the-shelf components of Multi-Modal Models.
CoRR
Erfan Shayegani, Yue Dong, Nael B. Abu-Ghazaleh
2023 J jnl
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks.
CoRR
Erfan Shayegani, Md Abdullah Al Mamun, Yu Fu, Pedram Zaree, Yue Dong, Nael B. Abu-Ghazaleh
2023 J jnl
That Doesn't Go There: Attacks on Shared State in Multi-User Augmented Reality Applications.
CoRR
Carter Slocum, Yicheng Zhang, Erfan Shayegani, Pedram Zaree, Nael B. Abu-Ghazaleh, Jiasi Chen