Related papers: BadGPT-4o: stripping safety finetuning from GPT mo…

With the recent proliferation of large language models (LLMs), enterprises have been able to rapidly develop proof-of-concepts and prototypes. As a result, there is a growing need to implement robust guardrails that monitor, quantize and…

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…

Large language models (LLMs) are increasingly deployed in real-world applications ranging from chatbots to agentic systems, where they are expected to process untrusted data and follow trusted instructions. Failure to distinguish between…

Safe fine-tuning defenses are often endorsed on the basis of a held-out gap reduction, but the same reduction can come from sampling noise, subject artifacts, capability loss, or a mechanism that does not transfer. We introduce Acceptance…

The ethical implications and potentials for misuse of Generative Artificial Intelligence are increasingly worrying topics. This paper explores how easily the default ethical guardrails of ChatGPT, using its latest customization features,…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mechanisms fail to generalize to harmful queries disguised by…

Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their robustness against sophisticated adversarial attacks remains poorly characterized. This study…

Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious purposes. Jailbreaking, which seeks to induce models to…

Jailbreak backdoor attacks on LLMs have garnered attention for their effectiveness and stealth. However, existing methods rely on the crafting of poisoned datasets and the time-consuming process of fine-tuning. In this work, we propose…

Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's…

Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image…

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak…

Large Language Models (LLMs), like ChatGPT, have demonstrated vast potential but also introduce challenges related to content constraints and potential misuse. Our study investigates three key research questions: (1) the number of different…

Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…

Machine learning is advancing rapidly, with applications bringing notable benefits, such as improvements in translation and code generation. Models like ChatGPT, powered by Large Language Models (LLMs), are increasingly integrated into…

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this complexity imposes a "jailbreak tax" that degrades the target model's task performance.…