Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as
they integrate more deeply into complex systems, the urgency to scrutinize their security …

With the significant development of large models in recent years, Large Vision-Language
Models (LVLMs) have demonstrated remarkable capabilities across a wide range of …

The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …

Automated red teaming holds substantial promise for uncovering and mitigating the risks
associated with the malicious use of large language models (LLMs), yet the field lacks a …

In response to rising concerns surrounding the safety, security, and trustworthiness of
Generative AI (GenAI) models, practitioners and regulators alike have pointed to AI red …

Are foundation models secure from malicious actors? In this work, we focus on the image
input to a vision-language model (VLM). We discover image hijacks, adversarial images that …

Safety alignment of Large Language Models (LLMs) can be compromised with manual
jailbreak attacks and (automatic) adversarial attacks. Recent work suggests that patching …

Abstract Large Language Models (LLMs) are increasingly being deployed in interactive
contexts that involve direct user engagement, such as chatbots and writing assistants. These …

Large language models (LLMs) can often be made to behave in undesirable ways that they
are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a …

The rapid evolution of artificial intelligence (AI) through developments in Large Language
Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements …