Related papers: Preference Redirection via Attention Concentration…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance on dynamic web content, however, makes them vulnerable to prompt injection attacks:…

As multimodal agents are increasingly trained to operate graphical user interfaces (GUIs) to complete user tasks, they face a growing threat from indirect prompt injection, attacks in which misleading instructions are embedded into the…

Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.…

Many engineering and scientific workflows rely on expensive black-box evaluations, requiring sequential decisions that must both improve task performance and reduce uncertainty. Bayesian optimization (BO) and Bayesian experimental design…

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and limited high-quality supervision. Existing filtered behavior…

Autonomous agents powered by large vision and language models (VLM) have demonstrated significant potential in completing daily computer tasks, such as browsing the web to book travel and operating desktop software, which requires agents to…

Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in…

Recent advancements in Latent Diffusion Models (LDMs) have revolutionized image synthesis and manipulation, raising significant concerns about data misappropriation and intellectual property infringement. While adversarial attacks have been…

Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives,…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to process multiple images as inputs. However, the vulnerabilities of multi-image MLLMs…

Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent attacks based on input transformations, such as random cropping, suggest that spatially…

Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if misused. However, existing benchmarks mainly evaluate LMs in chatbots or simple tool use. To more…

There is a growing interest in developing automated agents that can work alongside humans. In addition to completing the assigned task, such an agent will undoubtedly be expected to behave in a manner that is preferred by the human. This…

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…

The attention mechanism has been proven effective on various visual tasks in recent years. In the semantic segmentation task, the attention mechanism is applied in various methods, including the case of both Convolution Neural Networks…

Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by relying on a Vision-Language Model (VLM) to interpret screenshots and predict grounded…

Object-centric representations have recently enabled significant progress in tackling relational reasoning tasks. By building a strong object-centric inductive bias into neural architectures, recent efforts have improved generalization and…

Graphical User Interface (GUI) Agents powered by Multimodal Large Language Models (MLLMs) show significant potential for automating tasks. However, they often struggle with long-horizon tasks, leading to frequent failures. Process Reward…