241 citations · 838 across the 17 of their papers we have counts for
9 papers · 1 filter
On the Exploitability of Instruction Tuning
Manli Shu, Jiongxiao Wang, Chen Zhu +3
Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning…
ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger
Jiazhao Li, Yijin Yang, Zhuofeng Wu +2
Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in th…
Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
Xiaogeng Liu, Minghui Li, Haoyu Wang +5
Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can pr…
Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
Yulong Cao*, Ningfei Wang*, Chaowei Xiao* +6
In Autonomous Driving (AD) systems, perception is both security and safety critical. Despite various prior studies on its security issues, all of them only consider attacks on came…
Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
Yulong Cao, Chaowei Xiao, Benjamin Cyr +6
In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environm…
Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
Yulong Cao, Chaowei Xiao, Dawei Yang +4
Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbi…