Related papers: Compromising Embodied Agents with Contextual Backd…

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous,…

Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitable vulnerabilities…

Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…

A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

Recent advancements in Large Language Models (LLMs) have not only showcased impressive creative capabilities but also revealed emerging agentic behaviors that exploit linguistic ambiguity in adversarial settings. In this study, we…

Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks. LLMs thus hold tremendous potential for…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

This research introduces a novel approach to textual and multimodal Hate Speech Detection (HSD), using Large Language Models (LLMs) as dynamic knowledge bases to generate background context and incorporate it into the input of HSD…

Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated…

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

Neural contextual bandits are vulnerable to adversarial attacks, where subtle perturbations to rewards, actions, or contexts induce suboptimal decisions. We introduce AdvBandit, a black-box adaptive attack that formulates context poisoning…

Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP). Backdoor attacks initially verified that LLM is doing substantial harm at all stages,…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory…

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…

Security threats like prompt injection attacks pose significant risks to applications that integrate Large Language Models (LLMs), potentially leading to unauthorized actions such as API misuse. Unlike previous approaches that aim to detect…

Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations. They can support attack planning, adversary emulation, and the orchestration of multi-step activity such as lateral movement, a core…