Related papers: Follow My Eyes: Backdoor Attacks on VLM-based Scan…

Backdoor attacks embed malicious behaviors into Large Language Models (LLMs), enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of the implanted backdoors under user-driven post-deployment…

For VSLAM (Visual Simultaneous Localization and Mapping), localization is a challenging task, especially for some challenging situations: textureless frames, motion blur, etc.. To build a robust exploration and localization system in a…

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic…

Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fixed-token triggers…

The Internet of Things (IoT) systems increasingly depend on continual learning to adapt to non-stationary environments. These environments can include factors such as sensor drift, changing user behavior, device aging, and adversarial…

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…

Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critical applications. While backdoor attacks have been…

Robotic manipulation policies are increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and perception capabilities. Recently, inference-time attacks…

Prediction of pedestrian crossing intention is a critical function in autonomous vehicles. Conventional vision-based methods of crossing intention prediction often struggle with generalizability, context understanding, and causal reasoning.…

Autonomous driving systems face significant challenges in handling unpredictable edge-case scenarios, such as adversarial pedestrian movements, dangerous vehicle maneuvers, and sudden environmental changes. Current end-to-end driving models…

Gaze following estimates gaze targets of in-scene person by understanding human behavior and scene information. Existing methods usually analyze scene images for gaze following. However, compared with visual images, audio also provides…

Previous research on scanpath prediction has mainly focused on group models, disregarding the fact that the scanpaths and attentional behaviors of individuals are diverse. The disregard of these differences is especially detrimental to…

The prediction of human gaze behavior is important for building human-computer interactive systems that can anticipate a user's attention. Computer vision models have been developed to predict the fixations made by people as they search for…

Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer from efficiency and robustness. To address these challenges,…

Medical foundation models are gaining prominence in the medical community for their ability to derive general representations from extensive collections of medical image-text pairs. Recent research indicates that these models are…

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images…

Predicting where a person is looking is a complex task, requiring to understand not only the person's gaze and scene content, but also the 3D scene structure and the person's situation (are they manipulating? interacting or observing…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal diagnosis methods like model repairing or input robustness, yet these approaches are often…