Related papers: DECEIVE-AFC: Adversarial Claim Attacks against Sea…

Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications. However, concerns regarding their security, particularly the vulnerability to jailbreak attacks, persist. Drawing inspiration from adversarial…

Automated fact checking with large language models (LLMs) offers a scalable alternative to manual verification. Evaluating fact checking is challenging as existing benchmark datasets often include post claim analysis and annotator cues,…

Deep Reinforcement Learning (RL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decreasing the reward,…

Misinformation spreading over the Internet poses a significant threat to both societies and individuals, necessitating robust and scalable fact-checking that relies on retrieving accurate and trustworthy evidence. Previous methods rely on…

Large Language Models (LLMs) have recently demonstrated significant potential in time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world…

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…

With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks…

Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce harmful content. In this work, we introduce erase-and-check,…

TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These systems, which consist of multiple LLM-powered agents working…

Traditional fact-checking relies on humans to formulate relevant and targeted fact-checking questions (FCQs), search for evidence, and verify the factuality of claims. While Large Language Models (LLMs) have been commonly used to automate…

RL-based medical questionnaire systems have shown great potential in medical scenarios. However, their safety and robustness remain unresolved. This study performs a comprehensive evaluation on adversarial attack methods to identify and…

Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…

Function call capabilities have become crucial for Large Language Models (LLMs), enabling them to interact more effectively with external tools and APIs. Existing methods for improving the function call capabilities of LLMs rely on data…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…

The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation. However, the security…

Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These conversational search engines operate by loading retrieved website text into the LLM context for…

Large language models (LLMs) are increasingly being integrated into web browsers to create agentic browsing systems that execute actions on behalf of the user. Prior work considering the security of agentic browsers focuses exclusively on…

Mis- and disinformation are a substantial global threat to our security and safety. To cope with the scale of online misinformation, researchers have been working on automating fact-checking by retrieving and verifying against relevant…