Related papers: Red-teaming Activation Probes using Prompted LLMs

Existing efforts in safeguarding LLMs are limited in actively exposing the vulnerabilities of the target LLM and readily adapting to newly emerging safety risks. To address this, we present Purple-teaming LLMs with Adversarial Defender…

Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new…

Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…

Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting scheming, where agents covertly pursue misaligned goals. One approach to mitigating such…

Despite the substantial advancements in artificial intelligence, large language models (LLMs) remain being challenged by generation safety. With adversarial jailbreaking prompts, one can effortlessly induce LLMs to output harmful content,…

Final-token safety probes monitor a single hidden state after prompt prefill, but jailbreak prompts can contain probe-visible unsafe evidence distributed across earlier user-token representations that is missed by this readout. We study…

As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by other actors. When these inputs can be strategically shaped by…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Large Language Models (LLMs) deployed in enterprise settings (e.g., as Microsoft 365 Copilot) face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually…

Prompt injection poses a serious threat to the reliability and safety of LLM agents. Recent defenses against prompt injection, such as Instruction Hierarchy and SecAlign, have shown notable robustness against static attacks. However, to…

Despite recent advancements in Large Language Models (LLMs) and their alignment, they can still be jailbroken, i.e., harmful and toxic content can be elicited from them. While existing red-teaming methods have shown promise in uncovering…

Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as…

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…

The recent emergence of multimodal large language models (LLMs) has introduced new opportunities for improving visual hazard recognition on construction sites. Unlike traditional computer vision models that rely on domain-specific training…

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection attacks. In these attacks, malicious instructions embedded…

Prompt injection is one of the most critical vulnerabilities in LLM agents; yet, effective automated attacks remain largely unexplored from an optimization perspective. Existing methods heavily depend on human red-teamers and hand-crafted…

Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…

This paper analyzes Large Language Model (LLM) security vulnerabilities based on data from Crucible, encompassing 214,271 attack attempts by 1,674 users across 30 LLM challenges. Our findings reveal automated approaches significantly…

Text-to-image (T2I) models raise ethical and safety concerns due to their potential to generate inappropriate or harmful images. Evaluating these models' security through red-teaming is vital, yet white-box approaches are limited by their…