https://github.com/jwliang007/pff
공식 코드Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
Papers with Code 아카이브
Adversarial Attack
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/jxmorris12/second-order-adversarial-examples
공식 코드https://github.com/jzhang538/badmerging
공식 코드https://github.com/kaidi-jin/backdoor_samples_detection
공식 코드Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?
https://github.com/katiashh/ioi-attack
공식 코드IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
https://github.com/katiashh/uap_attack_on_quality_metrics
공식 코드Universal Perturbation Attack on Differentiable No-Reference Image- and Video-Quality Metrics
https://github.com/kay-ck/bsc-attack
공식 코드Attacking Video Recognition Models with Bullet-Screen Comments
https://github.com/khalooei/lsa
공식 코드Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework
https://github.com/kirinng/dwb
공식 코드Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
https://github.com/kishordgupta/GA_TEST_OWN
공식 코드Determining Sequence of Image Processing Technique (IPT) to Detect Adversarial Attacks
https://github.com/konpanousis/adversarial-lwta-autoattack
공식 코드Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness
https://github.com/kriegeskorte-lab/PNAS_2020_Controversial_Stimuli
공식 코드Controversial stimuli: pitting neural networks against each other as models of human recognition
https://github.com/ksandeshk/svd-uap
공식 코드Universalization of any adversarial attack using very few test examples
https://github.com/kxplaug/taa-bench
공식 코드https://github.com/labsix/adversarial-logit-pairing-analysis
공식 코드Evaluating and Understanding the Robustness of Adversarial Logit Pairing
https://github.com/lafeat/mora
공식 코드MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack
https://github.com/lan-lc/adversarial_example_of_Go
공식 코드Are AlphaZero-like Agents Robust to Adversarial Perturbations?
https://github.com/lancopku/Embedding-Poisoning
공식 코드https://github.com/lancopku/agent-backdoor-attacks
공식 코드Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
https://github.com/lasgroup/safetypolytope
공식 코드https://github.com/laujames/pat
공식 코드Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models
https://github.com/layumi/A_reID
공식 코드Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
https://github.com/layumi/Oxford-Paris-Attack
공식 코드Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
https://github.com/leileigan/clean_label_textual_backdoor_attack
공식 코드https://github.com/lethaiq/perturbations-in-the-wild
공식 코드https://github.com/levelower/vfa
공식 코드https://github.com/lfz/Guided-Denoise
공식 코드Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
https://github.com/lhf12278/saa
공식 코드https://github.com/lionel-w2/fap
공식 코드Few-Shot Adversarial Prompt Learning on Vision-Language Models
https://github.com/lions-epfl/charmer
공식 코드Revisiting Character-level Adversarial Attacks for Language Models
https://github.com/liuhwell/greedyfool
공식 코드https://github.com/liuyugeng/baadd
공식 코드https://github.com/liuzuxin/safe-rl-robustness
공식 코드On the Robustness of Safe Reinforcement Learning under Observational Perturbations
https://github.com/liyuuuu111/greater
공식 코드https://github.com/llm-attacks/llm-attacks
공식 코드Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/lmbtough/fsa
공식 코드Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attacks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.