Related papers: Attention! Your Vision Language Model Could Be Mal…
Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial…
The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of…
Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge.…
Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual modules introduces new challenges in terms of robustness for…
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…
The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want…
Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…
While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus…
Vision-Language Models (VLMs) have witnessed a surge in both research and real-world applications. However, as they are becoming increasingly prevalent, ensuring their robustness against adversarial attacks is paramount. This work…
Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images that control the behaviour of VLMs at inference time, and…
Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…
Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…
Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries.…
Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of…
The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security…
Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts. Investigating multimodal systems' robustness via…
Large vision-language models (LVLMs) have demonstrated their incredible capability in image understanding and response generation. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we…
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…
Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…
Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent…