← Keywords

data poisoning

128 papers

Explore in graph

Also known as

DPCL

Co-occurring keywords

backdoor attack (377) adversarial attack (1599) adversarial learning (1592) poisoning attack (97) adversarial defense (324) adversarial robustness (1335) adversarial training (1261) model security (118) backdoor defense (54) large language model (12755)

Papers

On the Exploitability of Instruction Tuning NIPS 2023
What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners? NIPS 2023
Poisoning-Based Backdoor Attacks in Computer Vision AAAI 2023
Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression ICML 2023
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks ICML 2023
BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking NIPS 2023
Rethinking Backdoor Attacks ICML 2023
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks NIPS 2023
CUDA: Convolution-Based Unlearnable Datasets CVPR 2023
Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems L4DC 2023
Black-Box Data Poisoning Attacks on Crowdsourcing IJCAI 2023
Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks NIPS 2023
Temporal Robustness against Data poisoning NIPS 2023
Data Poisoning Attacks Against Multimodal Encoders ICML 2023
Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems ACL 2023
Run-off Election: Improved Provable Defense against Data Poisoning Attacks ICML 2023
UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning EMNLP 2023
Computation and Data Efficient Backdoor Attacks ICCV 2023
Poisoning Language Models During Instruction Tuning ICML 2023
The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning ICCV 2023
On Collective Robustness of Bagging Against Data Poisoning ICML 2022
Autoregressive Perturbations for Data Poisoning NIPS 2022
Can Adversarial Training Be Manipulated By Non-Robust Features? NIPS 2022
Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification AAAI 2022
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation ICML 2022