English
Related papers

Related papers: Preference Redirection via Attention Concentration…

200 papers

Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge. Previous research has developed…

Machine Learning · Computer Science 2022-06-10 Lukas Struppek , Dominik Hintersdorf , Antonio De Almeida Correia , Antonia Adler , Kristian Kersting

The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. However, the evolving nature of…

Cryptography and Security · Computer Science 2026-05-11 Yanzhe Zhang , Diyi Yang

Attention mechanisms have raised significant interest in the research community, since they promise significant improvements in the performance of neural network architectures. However, in any specific problem, we still lack a principled…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Rafael Pedro , Arlindo L. Oliveira

Downstream fine-tuning of vision-language-action (VLA) models enhances robotics, yet exposes the pipeline to backdoor risks. Attackers can pretrain VLAs on poisoned data to implant backdoors that remain stealthy but can trigger harmful…

Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Miaosen Zhang , Xiaohan Zhao , Zhihong Tan , Zhou Huoshen , Yijia Fan , Yifan Yang , Kai Qiu , Bei Liu , Justin Wagle , Chenzhong Yin , Mingxi Cheng , Ji Li , Qi Dai , Chong Luo , Xu Yang , Xin Geng , Baining Guo

Vision foundation models are increasingly employed in autonomous driving systems due to their advanced capabilities. However, these models are susceptible to adversarial attacks, posing significant risks to the reliability and safety of…

Multimedia · Computer Science 2024-07-19 Jiyuan Fu , Zhaoyu Chen , Kaixun Jiang , Haijing Guo , Shuyong Gao , Wenqiang Zhang

Most existing One-Class Collaborative Filtering (OC-CF) algorithms estimate a user's preference as a latent vector by encoding their historical interactions. However, users often show diverse interests, which significantly increases the…

Information Retrieval · Computer Science 2020-10-27 Zheda Mai , Ga Wu , Kai Luo , Scott Sanner

Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant role, leaving the user role unaligned, and stick to a fixed…

Cryptography and Security · Computer Science 2025-04-08 Erfan Shayegani , G M Shahariar , Sara Abdali , Lei Yu , Nael Abu-Ghazaleh , Yue Dong

Recommendation systems (RS) have become indispensable tools for web services to address information overload, thus enhancing user experiences and bolstering platforms' revenues. However, with their increasing ubiquity, security concerns…

Cryptography and Security · Computer Science 2024-07-19 Xiaohao Liu , Zhulin Tao , Ting Jiang , He Chang , Yunshan Ma , Yinwei Wei , Xiang Wang

LLMs are increasingly deployed as autonomous agents with access to tools, databases, and external services, yet practitioners (across different sectors) lack systematic methods to assess how known threat classes translate into concrete…

Artificial Intelligence · Computer Science 2026-05-12 Tim Van hamme , Thomas Vissers , Javier Carnerero-Cano , Mario Fritz , Emil C. Lupu , Lieven Desmet , Dinil Mon Divakaran

Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based attacks that exploit over-privileged tool use. This paper aims to understand and mitigate…

Cryptography and Security · Computer Science 2026-01-21 Zimo Ji , Daoyuan Wu , Wenyuan Jiang , Pingchuan Ma , Zongjie Li , Yudong Gao , Shuai Wang , Yingjiu Li

Text-to-Image (T2I) models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work (NSFW) content. To investigate the…

Cryptography and Security · Computer Science 2025-08-07 Xinqi Lyu , Yihao Liu , Yanjie Li , Bin Xiao

Attention module does not always help deep models learn causal features that are robust in any confounding context, e.g., a foreground object feature is invariant to different backgrounds. This is because the confounders trick the attention…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Tan Wang , Chang Zhou , Qianru Sun , Hanwang Zhang

Large language models (LLMs) are becoming increasingly prevalent in modern software systems, interfacing between the user and the Internet to assist with tasks that require advanced language understanding. To accomplish these tasks, the LLM…

Cryptography and Security · Computer Science 2025-07-04 Sizhe Chen , Arman Zharmagambetov , Saeed Mahloujifar , Kamalika Chaudhuri , David Wagner , Chuan Guo

We introduce a resource allocation framework for goal-oriented semantic networks, where participating agents assess system quality through subjective (e.g., context-dependent) perceptions. To accommodate this, our model accounts for agents…

Information Theory · Computer Science 2025-06-06 Symeon Vaidanis , Photios A. Stavrou , Marios Kountouris

Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic…

Computation and Language · Computer Science 2025-06-16 Víctor Gallego

While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place…

Robotics · Computer Science 2025-05-15 Chaofan Zhang , Peng Hao , Xiaoge Cao , Xiaoshuai Hao , Shaowei Cui , Shuo Wang

Over the past decades, superplatforms, digital companies that integrate a vast range of third-party services and applications into a single, unified ecosystem, have built their fortunes on monopolizing user attention through targeted…

Artificial Intelligence · Computer Science 2025-05-26 Jianghao Lin , Jiachen Zhu , Zheli Zhou , Yunjia Xi , Weiwen Liu , Yong Yu , Weinan Zhang

Recent advancements in vision-language-action (VLA) models have shown promise in robotic manipulation, yet they continue to struggle with long-horizon, multi-step tasks. Existing methods lack internal reasoning mechanisms that can identify…

Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Akash Ghosh , Subhadip Baidya , Sriparna Saha , Xiuying Chen