Related papers: Playing Devil's Advocate: Unmasking Toxicity and V…
Large Vision-Language Models (LVLMs) have made significant strides in the field of video understanding in recent times. Nevertheless, existing video benchmarks predominantly rely on text prompts for evaluation, which often require complex…
Recent advancements in generative AI have led to the widespread adoption of large language models (LLMs) in software engineering, addressing numerous long-standing challenges. However, a comprehensive study examining the capabilities of…
We explore visual prompt injection (VPI) that maliciously exploits the ability of large vision-language models (LVLMs) to follow instructions drawn onto the input image. We propose a new VPI method, "goal hijacking via visual prompt…
Spurred by the recent rapid increase in the development and distribution of large language models (LLMs) across industry and academia, much recent work has drawn attention to safety- and security-related threats and vulnerabilities of LLMs,…
Large language models (LLMs) demonstrate considerable proficiency in numerous coding-related tasks; however, their capabilities in detecting software vulnerabilities remain limited. This limitation primarily stems from two factors: (1) the…
Large Language Models (LLMs) such as GPT and Llama2 are increasingly adopted in many safety-critical applications. Their security is thus essential. Even with considerable efforts spent on reinforcement learning from human feedback (RLHF),…
Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…
Large Vision Language Models (LVLMs) have demonstrated remarkable abilities in understanding and reasoning about both visual and textual information. However, existing evaluation methods for LVLMs, primarily based on benchmarks like Visual…
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.…
Warning: this paper includes model outputs showing offensive content. Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multimodal image/text generation. However, these models might also…
Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly…
This study explores real-world human interactions with large language models (LLMs) in diverse, unconstrained settings in contrast to most prior research focusing on ethically trimmed models like ChatGPT for specific tasks. We aim to…
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…
The emergence of Large Language Models (LLMs) has significantly influenced various aspects of software development activities. Despite their benefits, LLMs also pose notable risks, including the potential to generate harmful content and…
With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased significantly. One of these security risks is the threat of…
Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…
Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…
Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to…
Large Vision-Language Models (VLMs) are increasingly deployed in open-ended environments, where ensuring reliable safety under multimodal inputs is critical. However, existing evaluations remain largely instruction-centric, focusing on…
Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understudied, raising concerns about amplified misinformation in…