10 accepted papers
We have uncovered a powerful jailbreak technique that leverages large language models’ ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate and obfuscate previous attacks, our method dramatically outp…
Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we establish the largest public voice dataset to date, named DeepFakeVox-HQ, comprising 1.3 million samples, including 270…
Detecting text generated by Large Language Models (LLMs) is crucial, yet current detectors often struggle to generalize in open-world settings. We introduce Learning2Rewrite, a novel framework to detect LLM-generated text with exceptional generalization to unseen domains. Capitalized on the finding…
Mixed autonomy traffic systems face significant security challenges when malicious agents disrupt coordination between autonomous and human-driven vehicles. We present Malicious Agent Detection and Isolation (MADI), a framework addressing two critical forms of disruptive behavior: path order violati
In this letter, we address the critical security concerns in multi-agent systems, where illegal infiltration is commonly used to convert agents into malicious entities. Existing research predominantly focuses on explicit malicious attack patterns. Our work introduces a covert deception attack framew
Accurate pose estimation over SE(3) is fundamentally crucial for numerous perception tasks, including camera re-localization. While existing learning-based methods estimated from a series of RGB images have significantly improved the accuracy of pose, the majority of models still face one or two lim…
New ML models are often derived from existing ones (e.g., through fine-tuning, quantization or distillation), forming an ecosystem where models are *related* to each other and can share structure or even parameter values. Managing such a large and evolving ecosystem of model derivatives is challengi…
Multi-object tracking (MOT) in video sequences remains a challenging task, especially in scenarios with significant camera movements. This is because targets can drift considerably on the image plane, leading to erroneous tracking outcomes. Addressing such challenges typically requires supplementary…
Accurate absolute pose regression is one of the key challenges in robotics and computer vision. Existing direct regression methods suffer from two limitations. First, some noisy scenarios such as poor illumination conditions are likely to result in the uncertainty of pose estimation. Second, the out…
Fast and accurate pose estimation is essential for many robotic applications such as SLAM, manipulation, and 3D point registration. Existing solutions to this problem suffer from either high computation overhead due to the nonlinear features or accuracy loss due to linear approximation. In this pape…