paper-with-me

홈 › Papers

The art of defense: letting networks fool the attacker

2021-04-07 · Jinlai Zhang, Yinpeng Dong, Binbin Liu, Bo Ouyang, Jihong Zhu, Minchi Kuang, Houqing Wang, Yanmei Meng

Robust environment perception is critical for autonomous cars, and adversarial defenses are the most effective and widely studied ways to improve the robustness of environment perception. However, all of previous defense methods decrease the natural accuracy, and the nature of the DNNs itself has been overlooked. To this end, in this paper, we propose a novel adversarial defense for 3D point cloud classifier that makes full use of the nature of the DNNs. Due to the disorder of point cloud, all point cloud classifiers have the property of permutation invariant to the input point cloud. Based on this nature, we design invariant transformations defense (IT-Defense). We show that, even after accounting for obfuscated gradients, our IT-Defense is a resilient defense against state-of-the-art (SOTA) 3D attacks. Moreover, IT-Defense do not hurt clean accuracy compared to previous SOTA 3D defenses. Our code is available at: {\footnotesize{\url{https://github.com/cuge1995/IT-Defense}}}.

📄 PDF Abstract BibTeX arXiv:2104.02963

Code (1)

cuge1995/IT-Defense 공식 구현 pytorch

Tasks

Adversarial Defense

Similar Papers 제목 키워드 기반

Towards Certified Defense for Unrestricted Adversarial Attacks

2019-09-25 · Shengjia Zhao, Yang song, Stefano Ermon

Certified defenses against adversarial examples are very important in safety-critical applications of machine learning. However, existing certified defense strategies only safeguard against perturbation-based adversarial…

Adversarial Attack

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

2026-04-13 · Hanqi Xiao, Vaidehi Patil, Zaid Khan, Hyunji Lee 외 arxiv

As large language models (LLMs) become the engine behind conversational systems, their ability to reason about the intentions and states of their dialogue partners (i.e., form and use a theory-of-mind, or ToM) becomes in…

Reinforcement Learning

White-Box Adversarial Defense via Self-Supervised Data Estimation

2019-09-13 · Zudi Lin, Hanspeter Pfister, Ziming Zhang

In this paper, we study the problem of how to defend classifiers against adversarial attacks that fool the classifiers using subtly modified input data. In contrast to previous works, here we focus on the white-box adver…

Adversarial DefenseSelf-Supervised Learning

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization

2025-11-13 · Runpeng Geng, Yanting Wang, Chenlong Yin, Minhao Cheng 외 arxiv

Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an attacker-desired output. Existing prompt injection defenses are designed…

A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning

2025-04-28 · Greg Gluch, Shafi Goldwasser

In this paper, we initiate a cryptographically inspired theoretical study of detection versus mitigation of adversarial inputs produced by attackers of Machine Learning algorithms during inference time. We formally defin…