paper-with-me

Papers

Manipulating Trajectory Prediction with Backdoors

2023-12-21 · Kaouther Messaoud, Kathrin Grosse, Mickael Chen, Matthieu Cord, Patrick Pérez, Alexandre Alahi

Autonomous vehicles ought to predict the surrounding agents' trajectories to allow safe maneuvers in uncertain and complex traffic situations. As companies increasingly apply trajectory prediction in the real world, security becomes a relevant concern. In this paper, we focus on backdoors - a security threat acknowledged in other fields but so far overlooked for trajectory prediction. To this end, we describe and investigate four triggers that could affect trajectory prediction. We then show that these triggers (for example, a braking vehicle), when correlated with a desired output (for example, a curve) during training, cause the desired output of a state-of-the-art trajectory prediction model. In other words, the model has good benign performance but is vulnerable to backdoors. This is the case even if the trigger maneuver is performed by a non-casual agent behind the target vehicle. As a side-effect, our analysis reveals interesting limitations within trajectory prediction models. Finally, we evaluate a range of defenses against backdoors. While some, like simple offroad checks, do not enable detection for all triggers, clustering is a promising candidate to support manual inspection to find backdoors.

📄 PDF Abstract BibTeX arXiv:2312.13863

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous VehiclesPredictionTrajectory Prediction

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Under-confidence Backdoors Are Resilient and Stealthy Backdoors

2022-02-19 · Minlong Peng, Zidi Xiong, Quang H. Nguyen, Mingming Sun 외

By injecting a small number of poisoned samples into the training set, backdoor attacks aim to make the victim model produce designed outputs on any input injected with pre-designed backdoors. In order to achieve a high …

Backdoor Attack

Backdooring and Poisoning Neural Networks with Image-Scaling Attacks

2020-03-19 · Erwin Quiring, Konrad Rieck

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the …

Manipulating SGD with Data Ordering Attacks

2021-04-19 · NeurIPS 2021 12 · Ilia Shumailov, Zakhar Shumaylov, Dmitry Kazhdan, Yiren Zhao 외

Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this …

Backdoors in Neural Models of Source Code

2020-06-11 · Goutham Ramakrishnan, Aws Albarghouthi

Deep neural networks are vulnerable to a range of adversaries. A particularly pernicious class of vulnerabilities are backdoors, where model predictions diverge in the presence of subtle triggers in inputs. An attacker c…

Rethinking Backdoor Detection Evaluation for Language Models

2024-08-31 · Jun Yan, Wenjie Jacky Mo, Xiang Ren, Robin Jia

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. Backdoor detection methods ai…