相关论文: Simulated Ensemble Attack: Transferring Jailbreaks…

Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parameter updates, and reusable components opens entry points for attackers. Threats have…

Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model…

Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…

Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…

Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…

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…

With much longer optimization time than that of untargeted attacks notwithstanding, the transferability of targeted attacks is still far from satisfactory. Recent studies reveal that fine-tuning an existing adversarial example (AE) in…

Large Vision-Language Models (VLMs) are susceptible to jailbreak attacks: researchers have developed a variety of attack strategies that can successfully bypass the safety mechanisms of VLMs. Among these approaches, jailbreak methods based…

Large Language Models (LLMs) and Vision-Language Models (VLMs) remain highly vulnerable to textual and visual jailbreaks, as well as prompt injections (arXiv:2307.15043, Greshake et al., 2023, arXiv:2306.13213). Existing defenses often…

With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted…

Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, failing to disrupt proprietary LLMs consistently. To reliably…

Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual inputs. However, despite recent advances in safety alignment, MLLMs remain vulnerable to…

The distributed (federated) LLM is an important method for co-training the domain-specific LLM using siloed data. However, maliciously stealing model parameters and data from the server or client side has become an urgent problem to be…

Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety mechanism vulnerabilities. Jailbreak attacks are red teaming…

As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable the safety mechanism of LLMs -- has attracted growing…

Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been…

Recently, Large Reasoning Models (LRMs) have demonstrated superior logical capabilities compared to traditional Large Language Models (LLMs), gaining significant attention. Despite their impressive performance, the potential for stronger…

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential…