10 accepted papers
With the widespread deployment of deep learning models in multi-party collaborative scenarios, the issues of secure model access control and intellectual property (IP) protection have become increasingly critical. To address the limitations of existing methods that lack proactive defense mechanisms
Robot navigation systems are critical for various real-world applications such as delivery services, hospital logistics, and warehouse management. Although classical navigation methods provide interpretability, they rely heavily on expert manual tuning, limiting their adaptability. Conversely, purel
LLMs are increasingly developed through distributed supply chains, where model providers create base models that deployers customize with system prompts for task-specific applications and safety alignment. We introduce SHIP, a novel post-deployment attack that bypasses system prompts, enabling unres…
LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation of user intent, leading to the agent’s actions that diverge from the user’s intended goal, especially as external toolkit…
Assessing the safety of autonomous driving (AD) systems against security threats, particularly backdoor attacks, is a stepping stone for real-world deployment. However, existing works mainly focus on pixel-level triggers which are impractical to deploy in the real world. We address this gap by intro…
Continual test-time domain adaptation (CTTA) aims to adapt the source pre-trained model to a continually changing target domain without additional data acquisition or labeling costs. This issue necessitates an initial performance enhancement within the present domain without labels while concurrentl…
Recent studies developed jailbreaking attacks, which construct jailbreaking prompts to "fool" LLMs into responding to harmful questions. Early-stage jailbreaking attacks require access to model internals or significant human efforts. More advanced attacks utilize genetic algorithms for automatic an…
Backdoor attacks pose a severe threat to the supply chain management of deep reinforcement learning (DRL) policies. Despite initial defenses proposed in recent studies, these methods have very limited generalizability and scalability. To address this issue, we propose BIRD, a technique to detect and…
Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes. Current detection mechanisms are limited by their inability to a…
In multi-label brain tumor segmentation, class imbalance and inter-class interference are common and challenging problems. In this paper, we propose a novel end-to-end trainable network named FSENet to address the aforementioned issues. The proposed FSENet has a tumor region pooling component to res…