Pith. sign in

REVIEW 6 cited by

Adversarial Training: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2410.15042 v1 pith:V5OEK5N7 submitted 2024-10-19 cs.LG cs.AI

Mengnan Zhao , Lihe Zhang , Jingwen Ye , Huchuan Lu , Baocai Yin , Xinchao Wang This is my paper · ORCID
classification cs.LGcs.AI
keywords adversarialtrainingcomprehensiverecentstudiessurveyaddressesaltered
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Solver-Integrated Adversarial Attacking and Training of Neural Operators

    cs.LG 2025-10 conditional novelty 6.0 of 10

    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.

  2. Adversarial Suffix Filtering: a Defense Pipeline for LLMs

    cs.LG 2025-05 conditional novelty 6.0 of 10

    ASF detects and removes adversarial suffixes by segmenting prompts and classifying each segment with a fine-tuned BERT model, reducing jailbreak success on several LLMs while leaving normal-task performance roughly intact.

  3. Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates

    cs.LG 2026-07 conditional novelty 5.0 of 10

    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.

  4. NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations

    cs.CV 2025-10 conditional novelty 5.0 of 10

    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 ...

  5. Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems

    cs.RO 2025-05 conditional novelty 4.0 of 10

    Adversarial attacks shift OpenPilot distance estimates by tens of meters and cut YOLOv8 stop sign recall sharply, while tested defenses trade off gains against new failure modes.

  6. A Survey on False Information Detection: From A Perspective of Propagation on Social Networks

    cs.SI 2025-06 conditional novelty 3.0 of 10

    A survey that organizes propagation-based false information detection into homogeneous and heterogeneous categories, summarizing datasets, methods, and future directions.

Pith tools