Papers with Code 아카이브

Adversarial Attack

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 4
평가표: 3
보존된 평가 기록: 9

An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.

Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/zhengliz/natural-adversary

공식 코드

Generating Natural Adversarial Examples

https://github.com/zhenxianglance/cbd

공식 코드

CBD: A Certified Backdoor Detector Based on Local Dominant Probability

https://github.com/zhipeng-wei/tt

공식 코드

Boosting the Transferability of Video Adversarial Examples via Temporal Translation

https://github.com/zhipenghe/imperceptibility-of-tabular-adversarial-attack

공식 코드

Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysis

https://github.com/zhipenghe/tabattackbench

공식 코드

TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data

https://github.com/zhongliangguo/acdm

공식 코드

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack

https://github.com/zhongliangguo/fp-attack

공식 코드

A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models

https://github.com/zhonglifr/gxattack

공식 코드

Explainable Graph Neural Networks Under Fire

https://github.com/zhongxuanwang/adv_attk

공식 코드

Susceptibility of Adversarial Attack on Medical Image Segmentation Models

https://github.com/zhou-cybersecurity-ai/synghost

공식 코드

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

https://github.com/zhouying20/hmgc

공식 코드

Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack

https://github.com/zhouzhengqd/beard

공식 코드

BEARD: Benchmarking the Adversarial Robustness for Dataset Distillation

https://github.com/zhpinkman/robust-prototype-learning

공식 코드

Robust Text Classification: Analyzing Prototype-Based Networks

https://github.com/zhuhai-ustc/limeattack

공식 코드

LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack

https://github.com/zihao-ai/bot

공식 코드

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

https://github.com/zihao-ai/unthinking_vulnerability

공식 코드

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

https://github.com/zihao-ai/vdc

공식 코드

VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models

https://github.com/zjwei-nuist/SRAE

공식 코드

Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks

https://github.com/ztcoalson/waffle

공식 코드

BERT Lost Patience Won't Be Robust to Adversarial Slowdown

https://github.com/zzwjames/dpgba

공식 코드

Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective

https://gitlab.com/Atanukundu/FlexiFal

공식 코드

Data-Driven Falsification of Cyber-Physical Systems

https://gitlab.com/awadailab/faithful-contrastive-explanations

공식 코드

Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations

https://gitlab.idiap.ch/bob/bob.paper.neurips2024_model_pairing/

공식 코드

Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks

https://gitlab.inria.fr/tmaho/robustness_benchmark

공식 코드

RoBIC: A benchmark suite for assessing classifiers robustness

https://worksheets.codalab.org/worksheets/0x822ba2f9005f49f08755a84443c76456

공식 코드

Defending against Whitebox Adversarial Attacks via Randomized Discretization

https://worksheets.codalab.org/worksheets/0xa21e794020bb474d8804ec7bc0543f52

공식 코드

Certified Defenses against Adversarial Examples

https://github.com/1konny/vib-pytorch

Deep Variational Information Bottleneck

https://github.com/2023-MindSpore-1/ms-code-222/tree/main/resnet

ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies

https://github.com/2023-MindSpore-4/Code12/tree/main/ganleilei/CleanLabelBackdoorAttackMindspore-master

Triggerless Backdoor Attack for NLP Tasks with Clean Labels

https://github.com/2024-MindSpore-1/Code4/tree/main/ResNet

ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies

https://github.com/AI-secure/Transferability-Reduced-Smooth-Ensemble

Towards Deep Learning Models Resistant to Adversarial Attacks

https://github.com/Abhis-123/TextToImage

Generative Adversarial Text to Image Synthesis

https://github.com/AishrithRao/robust-physical-attack

ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector

https://github.com/AlanChou/Adversarial-Training-for-Free

Adversarial Training for Free!

https://github.com/AliLotfi92/Deep-Variational-Information-Bottlenck

Deep Variational Information Bottleneck

https://github.com/AliLotfi92/Deep_Variational_Information_Bottlenck

Deep Variational Information Bottleneck

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.