paper-with-me

Papers

Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems

2023-03-24 · Yue Wang, Wending Li, Michail Maniatakos, Saif Eddin Jabari

Deep Reinforcement Learning (DRL) enhances the efficiency of Autonomous Vehicles (AV), but also makes them susceptible to backdoor attacks that can result in traffic congestion or collisions. Backdoor functionality is typically incorporated by contaminating training datasets with covert malicious data to maintain high precision on genuine inputs while inducing the desired (malicious) outputs for specific inputs chosen by adversaries. Current defenses against backdoors mainly focus on image classification using image-based features, which cannot be readily transferred to the regression task of DRL-based AV controllers since the inputs are continuous sensor data, i.e., the combinations of velocity and distance of AV and its surrounding vehicles. Our proposed method adds well-designed noise to the input to neutralize backdoors. The approach involves learning an optimal smoothing (noise) distribution to preserve the normal functionality of genuine inputs while neutralizing backdoors. By doing so, the resulting model is expected to be more resilient against backdoor attacks while maintaining high accuracy on genuine inputs. The effectiveness of the proposed method is verified on a simulated traffic system based on a microscopic traffic simulator, where experimental results showcase that the smoothed traffic controller can neutralize all trigger samples and maintain the performance of relieving traffic congestion

📄 PDF Abstract BibTeX arXiv:2303.14197

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous VehiclesDeep Reinforcement Learningimage-classificationImage Classification

Similar Papers 제목 키워드 기반

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

2020-02-26 · Binghui Wang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…

Backdoor Attack

Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs

2026-06-02 · Lisa Bouger, Théo Lasnier, Philippe Loubet Moundi, Yannick Teglia 외 arxiv

Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the…

Continual Pretraining

Backdoor Smoothing: Demystifying Backdoor Attacks on Deep Neural Networks

2020-06-11 · Kathrin Grosse, Taesung Lee, Battista Biggio, Youngja Park 외

Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorith…

Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models

2026-01-07 · San Kim, Gary Geunbae Lee arxiv

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their relian…

LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning

2024-04-19 · Beichen Li, Yuanfang Guo, Heqi Peng, Yangxi Li 외

Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most …

Backdoor Attackbackdoor defense