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

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

LLM jailbreaks are a widespread safety challenge. Given this problem has not yet been tractable, we suggest targeting a key failure mechanism: the failure of safety to generalize across semantically equivalent inputs. We further focus the…

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

Neural networks have demonstrated remarkable success in learning and solving complex tasks in a variety of fields. Nevertheless, the rise of those networks in modern computing has been accompanied by concerns regarding their vulnerability…

Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle…

Model extraction attacks are one type of inference-time attacks that approximate the functionality and performance of a black-box victim model by launching a certain number of queries to the model and then leveraging the model's predictions…

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

We introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variations of a prompt with a combination of augmentations - such…

Jailbreaking methods, which induce Multi-modal Large Language Models (MLLMs) to output harmful responses, raise significant safety concerns. Among these methods, gradient-based approaches, which use gradients to generate malicious prompts,…

Safety alignment in large language models (LLMs) is increasingly compromised by jailbreak attacks, which can manipulate these models to generate harmful or unintended content. Investigating these attacks is crucial for uncovering model…

Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent structural responsiveness. We observe that such prompts…

Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness but, more critically, by its stealthiness. However, existing…

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom…

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to…

With the introduction of the transformers architecture, LLMs have revolutionized the NLP field with ever more powerful models. Nevertheless, their development came up with several challenges. The exponential growth in computational power…

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-scale, reproducible infrastructure for generating,…