Related papers: Model-Agnostic Lifelong LLM Safety via Externalize…

Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

While large language models (LLMs) excel at static scientific reasoning, they struggle to model the temporal structure of dynamic physical processes. We present EvoMD-LLM (Evolutionary Molecular Dynamics Large Language Model), a framework…

Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a black-box evolutionary framework that tests model safety by evolving prompts in a synchronous…

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain…

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks. However, lacking…

As Large Language Models (LLMs) are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety concerns, especially those evolving over multi-round interactions. Existing defenses are…

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of…

Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent work has shown that it is highly vulnerable to poisoning-based backdoor attacks operating…

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…

In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a…

Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing approaches often rely on static heuristics or stochastic search, rendering them brittle…

Various jailbreak attacks have been proposed to red-team Large Language Models (LLMs) and revealed the vulnerable safeguards of LLMs. Besides, some methods are not limited to the textual modality and extend the jailbreak attack to…

Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise safety alignment and lead to harmful outputs. Existing…