Related papers: Speech-Audio Compositional Attacks on Multimodal L…
System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…
Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat…
Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores,…
Hearing is arguably an essential ability of artificial intelligence (AI) agents in the physical world, which refers to the perception and understanding of general auditory information consisting of at least three types of sounds: speech,…
This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…
Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…
Full-duplex multimodal large language models (LLMs) provide a unified framework for addressing diverse speech understanding and generation tasks, enabling more natural and seamless human-machine conversations. Unlike traditional modularised…
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) can generate content spanning ideological rhetoric to explicit instructions for violence. However, existing safety evaluations often rely on simplistic binary labels (safe and unsafe), overlooking the nuanced…
Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial prompting. Existing automated methods are increasingly effective but each commits to a…
Large language model (LLM) agents have shown impressive capabilities in human language comprehension and reasoning, yet their potential in cybersecurity remains underexplored. We introduce DefenderBench, a practical, open-source toolkit for…
Ensuring the safety and alignment of Large Language Models is a significant challenge with their growing integration into critical applications and societal functions. While prior research has primarily focused on jailbreak attacks, less…
With the growing prevalence of large language models (LLMs), the safety of LLMs has raised significant concerns. However, there is still a lack of definitive standards for evaluating their safety due to the subjective nature of current…
Audio Large language models (LLMs) are increasingly deployed in the real world, where they inevitably capture speech from unintended nearby bystanders, raising privacy risks that existing benchmarks and defences did not consider. We…
Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…
Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…
Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful…
Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…
With the increasingly deep integration of large language models (LLMs) across diverse domains, the effectiveness of their safety mechanisms is encountering severe challenges. Currently, jailbreak attacks based on prompt engineering have…
When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…