相关论文: Towards Transferable Attacks Against Vision-LLMs i…

Large vision-language models (VLMs) for autonomous driving (AD) are evolving beyond perception and cognition tasks toward motion planning. However, we identify two critical challenges in this direction: (1) VLMs tend to learn shortcuts by…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

As the AI systems become deeply embedded in social media platforms, we've uncovered a concerning security vulnerability that goes beyond traditional adversarial attacks. It becomes important to assess the risks of LLMs before the general…

Recent advances in machine learning, especially techniques such as deep neural networks, are enabling a range of emerging applications. One such example is autonomous driving, which often relies on deep learning for perception. However,…

The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…

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…

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.…

Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to unintended privacy leakage. While adversarial image…

End-to-end autonomous driving systems built on Vision Language Models (VLMs) have shown significant promise, yet their reliance on autoregressive architectures introduces some limitations for real-world applications. The sequential,…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to LLMs form Vision Language Models (VLMs). However, recent research shows that the visual modality in VLMs is highly…

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…

Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images…

The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing…

Physical adversarial attacks on road signs are continuously exploiting vulnerabilities in modern day autonomous vehicles (AVs) and impeding their ability to correctly classify what type of road sign they encounter. Current models cannot…

Visual Question Answering (VQA) models, which fall under the category of vision-language models, conventionally execute multiple downsampling processes on image inputs to strike a balance between computational efficiency and model…

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 Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…

Existing benchmarks for Vision-Language Model (VLM) on autonomous driving (AD) primarily assess interpretability through open-form visual question answering (QA) within coarse-grained tasks, which remain insufficient to assess capabilities…

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…

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed…