paper-with-me

홈 › Papers

Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors

2024-06-21 · Peter Lorenz, Mario Fernandez, Jens Müller, Ullrich Köthe

Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in real-world scenarios. In recent years, many OOD detectors have been developed, and even the benchmarking has been standardized, i.e. OpenOOD. The number of post-hoc detectors is growing fast. They are showing an option to protect a pre-trained classifier against natural distribution shifts and claim to be ready for real-world scenarios. However, its effectiveness in dealing with adversarial examples (AdEx) has been neglected in most studies. In cases where an OOD detector includes AdEx in its experiments, the lack of uniform parameters for AdEx makes it difficult to accurately evaluate the performance of the OOD detector. This paper investigates the adversarial robustness of 16 post-hoc detectors against various evasion attacks. It also discusses a roadmap for adversarial defense in OOD detectors that would help adversarial robustness. We believe that level 1 (AdEx on a unified dataset) should be added to any OOD detector to see the limitations. The last level in the roadmap (defense against adaptive attacks) we added for integrity from an adversarial machine learning (AML) point of view, which we do not believe is the ultimate goal for OOD detectors.

📄 PDF Abstract BibTeX arXiv:2406.15104

Code (1)

adverml/advopenood 공식 구현 pytorch

Tasks

Adversarial DefenseAdversarial RobustnessBenchmarking

Similar Papers 제목 키워드 기반

Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-modal Fake News Detection

2022-06-17 · Jinyin Chen, Chengyu Jia, Haibin Zheng, Ruoxi Chen 외

The proliferation of fake news and its serious negative social influence push fake news detection methods to become necessary tools for web managers. Meanwhile, the multi-media nature of social media makes multi-modal fa…

Backdoor AttackFake News Detection

Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks

2024-07-30 · Yunfeng Diao, Naixin Zhai, Changtao Miao, Zitong Yu 외

Recent advancements in image synthesis, particularly with the advent of GAN and Diffusion models, have amplified public concerns regarding the dissemination of disinformation. To address such concerns, numerous AI-genera…

Adversarial AttackAdversarial RobustnessImage Generation

Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection

2024-12-09 · Caiyun Xie, Dengpan Ye, Yunming Zhang, Long Tang 외

The security of AI-generated content (AIGC) detection is crucial for ensuring multimedia content credibility. To enhance detector security, research on adversarial attacks has become essential. However, most existing adv…

Adversarial Attack

On the Importance of Backbone to the Adversarial Robustness of Object Detectors

2023-05-27 · Xiao Li, Hang Chen, Xiaolin Hu

Object detection is a critical component of various security-sensitive applications, such as autonomous driving and video surveillance. However, existing object detectors are vulnerable to adversarial attacks, which pose…

Adversarial RobustnessAutonomous DrivingObjectobject-detection+2

GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives

2026-05-09 · Alexandre Le Mercier, Chris Develder, Thomas Demeester arxiv

In multi-agent systems (MAS), a single deceptive agent can nullify all gains of an agentic AI collective and evade deployed defenses. However, existing adversarial studies on MAS target only shallow tasks and do not cons…

Adversarial Robustness