Related papers: Dynamic Target Attack

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

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…

Jailbreak attacks exploit specific prompts to bypass LLM safeguards, causing the LLM to generate harmful, inappropriate, and misaligned content. Current jailbreaking methods rely heavily on carefully designed system prompts and numerous…

Efficient red-teaming method to uncover vulnerabilities in Large Language Models (LLMs) is crucial. While recent attacks often use LLMs as optimizers, the discrete language space make gradient-based methods struggle. We introduce LARGO…

Jailbreak vulnerabilities in Large Language Models (LLMs) refer to methods that extract malicious content from the model by carefully crafting prompts or suffixes, which has garnered significant attention from the research community.…

Direct Preference Optimization (DPO) is an efficient alignment technique that steers LLMs towards preferable outputs by training on preference data, bypassing the need for explicit reward models. Its simplicity enables easy adaptation to…

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Recent studies developed jailbreaking attacks, which construct jailbreaking prompts to fool LLMs into responding to harmful questions. Early-stage jailbreaking attacks require access to model internals or significant human efforts. More…

Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…

Many recent studies showed that LLMs are vulnerable to jailbreak attacks, where an attacker can perturb the input of an LLM to induce it to generate an output for a harmful question. In general, existing jailbreak techniques either optimize…

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

Recent work on adversarial attack has shown that Projected Gradient Descent (PGD) Adversary is a universal first-order adversary, and the classifier adversarially trained by PGD is robust against a wide range of first-order attacks. It is…

Jailbreak attacks against large language models (LLMs) aim to induce harmful behaviors in LLMs through carefully crafted adversarial prompts. To mitigate attacks, one way is to perform adversarial training (AT)-based alignment, i.e.,…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack…

Existing black-box jailbreak attacks achieve certain success on non-reasoning models but degrade significantly on recent SOTA reasoning models. To improve attack ability, inspired by adversarial aggregation strategies, we integrate multiple…

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…

Transfer-based adversarial attacks raise a severe threat to real-world deep learning systems since they do not require access to target models. Adversarial training (AT), which is recognized as the strongest defense against white-box…