相关论文: Adaptive Deployment of Untrusted LLMs Reduces Dist…

Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…

While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become common to collect data from the Internet or hire a third party…

As large language models (LLMs) continue to evolve, it is critical to assess the security threats and vulnerabilities that may arise both during their training phase and after models have been deployed. This survey seeks to define and…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks,…

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…

Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can…

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak…

Large Language Models (LLMs) are set to reshape cybersecurity by augmenting red and blue team operations. Red teams can exploit LLMs to plan attacks, craft phishing content, simulate adversaries, and generate exploit code. Conversely, blue…

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…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Previous learning-based vulnerability detection methods relied on either medium-sized pre-trained models or smaller neural networks from scratch. Recent advancements in Large Pre-Trained Language Models (LLMs) have showcased remarkable…

As Large Language Models (LLMs) proliferate, developing privacy safeguards for these models is crucial. One popular safeguard involves training LLMs in a differentially private manner. However, such solutions are shown to be computationally…

Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research…

This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model (LLM) safety evaluation from a constrained example-based approach to a more expansive and effective policy-based…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Large Language Models (LLMs) are increasingly used in healthcare, yet ensuring their safety and trustworthiness remains a barrier to deployment. Conversational medical assistants must avoid unsafe compliance without over-refusing benign…

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…