REVIEW 4 cited by
Adversarial Training: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the effectiveness of AT in improving the robustness of deep neural networks against diverse adversarial attacks. However, a comprehensive overview of these developments is still missing. This survey addresses this gap by reviewing a broad range of recent and representative studies. Specifically, we first describe the implementation procedures and practical applications of AT, followed by a comprehensive review of AT techniques from three perspectives: data enhancement, network design, and training configurations. Lastly, we discuss common challenges in AT and propose several promising directions for future research.
Forward citations
Cited by 4 Pith papers
-
Solver-Integrated Adversarial Attacking and Training of Neural Operators
Solver-integrated PGD attacks produce stronger adversarial examples for neural operators than dictionary-based attacks, and round-based retraining improves some out-of-distribution accuracy but with mixed, costly results.
-
Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates
Combining suffix-window representation finetuning with an ActGrad-pruned surrogate cuts latent-adversarial-training FLOPs per step by 48.1% with only 0.0118% trainable parameters, while accepting higher attack success rates.
-
NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
By modeling the attack as a known transformation with unknown parameters, NAPPure jointly recovers the clean image and the perturbation through likelihood maximization, beating additive-only purification baselines on ...
-
A Survey on False Information Detection: From A Perspective of Propagation on Social Networks
A survey that organizes propagation-based false information detection into homogeneous and heterogeneous categories, summarizing datasets, methods, and future directions.
Discussion (0). Sign in to comment.