相关论文: AntiDote: Bi-level Adversarial Training for Tamper…

Despite their performance, Artificial Neural Networks are not reliable enough for most of industrial applications. They are sensitive to noises, rotations, blurs and adversarial examples. There is a need to build defenses that protect…

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

Deep learning models have shown considerable vulnerability to adversarial attacks, particularly as attacker strategies become more sophisticated. While traditional adversarial training (AT) techniques offer some resilience, they often focus…

Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with…

Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly operate at the token level, where an injected trigger causes…

As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial…

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While…

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to…

Recent advances in the development of large language models have resulted in public access to state-of-the-art pre-trained language models (PLMs), including Generative Pre-trained Transformer 3 (GPT-3) and Bidirectional Encoder…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…

The rapid progress in open-source Large Language Models (LLMs) is significantly driving AI development forward. However, there is still a limited understanding of their trustworthiness. Deploying these models at scale without sufficient…

In this paper, we tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs) with a novel dual-stage optimisation technique using adversarial fine-tuning. Our two-pronged approach employs an…

This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these…

The growth of highly advanced Large Language Models (LLMs) constitutes a huge dual-use problem, making it necessary to create dependable AI-generated text detection systems. Modern detectors are notoriously vulnerable to adversarial…