MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer. Recent methods demonstrate this risk, but they are usually...

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic Via Asymmetric Contrastive Learning

Decompositional jailbreaks pose a critical threat to large language models LLMs by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collectively reconstruct prohibited content. In real-world deployments, LLMs face a continuous, untraceable...

HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense

Jailbreak attacks pose significant threats to large language models LLMs, enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where attackers continuously deepen their attacks to exploit...

Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks

The rapid proliferation of Large Language Models LLMs has raised significant concerns about their security against adversarial attacks. In this work, we propose a novel approach to crafting universal jailbreaks and data extraction attacks by exploiting latent space discontinuities, an architectur...

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks

Large language models LLMs are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rely on passive rejection, which either fails against adaptive attackers or overly...

RedTWIZ: Diverse LLM Red Teaming Via Adaptive Attack Planning

This paper presents the vision, scientific contributions, and technical details of RedTWIZ: an adaptive and diverse multi-turn red teaming framework, to audit the robustness of Large Language Models LLMs in AI-assisted software development. Our work is driven by three major research streams: 1...

NEXUS: Network Exploration for EXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks

Large Language Models LLMs have revolutionized natural language processing but remain vulnerable to jailbreak attacks, especially multi-turn jailbreaks that distribute malicious intent across benign exchanges and bypass alignment mechanisms. Existing approaches often explore the adversarial space...

Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models

Large Language Models LLMs are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety mechanisms. Unlike overt attacks, these subtle prompts exploit...

CCFC: Core and Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection

Jailbreak attacks pose a serious challenge to the safe deployment of large language models LLMs. We introduce CCFC Core & Core-Full-Core, a dual-track, prompt-level defense framework designed to mitigate LLMs' vulnerabilities from prompt injection and structure-aware jailbreak attacks. CCFC...

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection

Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new attacks, degrade model responses to benign prompts, or...

ARMOR: Aligning Secure and Safe Large Language Models Via Meticulous Reasoning

Large Language Models LLMs have demonstrated remarkable generative capabilities. However, their susceptibility to misuse has raised significant safety concerns. While post-training safety alignment methods have been widely adopted, LLMs remain vulnerable to malicious instructions that can bypass...

Advancing Jailbreak Strategies: a Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses

The advancement of Pre-Trained Language Models PTLMs and Large Language Models LLMs has led to their widespread adoption across diverse applications. Despite their success, these models remain vulnerable to attacks that exploit their inherent weaknesses to bypass safety measures. Two primary...

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment

Safely aligning large language models LLMs often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on complex iterative prompting or auxiliary models. To address...

Alignment under Pressure: the Case for Informed Adversaries When Evaluating LLM Defenses

Large language models LLMs are rapidly deployed in real-world applications ranging from chatbots to agentic systems. Alignment is one of the main approaches used to defend against attacks such as prompt injection and jailbreaks. Recent defenses report near-zero Attack Success Rates ASR even again...

JULI: Jailbreak Large Language Models by Self-Introspection

Large Language Models LLMs are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as necessitating access to the model weights or the generation process...

Red Teaming the Mind of the Machine: a Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Large Language Models LLMs are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment safeguards. This paper provides a systematic investigation o...

Security Steerability Is All You Need

The adoption of Generative AI GenAI in various applications inevitably comes with expanding the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim to mitigate these security threats in GenAI by developing...

JailbreaksOverTime: Detecting Jailbreak Attacks under Distribution Shift

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback RLHF 32, language models remain vulnerable to jailbreak attacks that bypass safety guardrails. Universal jailbreaks - prefixes that can circumvent alignment fo...

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

Multi-turn interactions with language models LMs pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and diversity remain among the key challenges of multi-turn...

Apple Releases Urgent iOS Updates to Patch New Zero-Day Bug

Apple on Monday rushed out a security update for iOS 15.0.2 and iPadOS 15.0.2 to fix a remote code-execution RCE zero-day vulnerability that’s being actively exploited. Within hours, a security researcher had picked the bug apart and published both proof-of-concept code and an explanation of the...