Pith. sign in

REVIEW 6 cited by

Are adversarial examples inevitable?

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

arxiv 1809.02104 v3 pith:H7QSNW4Q submitted 2018-09-06 cs.LG cs.CVstat.ML

classification cs.LGcs.CVstat.ML
keywords adversarialattacksexamplesdefensesclassifierfundamentalinevitableproblems
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

A wide range of defenses have been proposed to harden neural networks against adversarial attacks. However, a pattern has emerged in which the majority of adversarial defenses are quickly broken by new attacks. Given the lack of success at generating robust defenses, we are led to ask a fundamental question: Are adversarial attacks inevitable? This paper analyzes adversarial examples from a theoretical perspective, and identifies fundamental bounds on the susceptibility of a classifier to adversarial attacks. We show that, for certain classes of problems, adversarial examples are inescapable. Using experiments, we explore the implications of theoretical guarantees for real-world problems and discuss how factors such as dimensionality and image complexity limit a classifier's robustness against adversarial examples.

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. Existence of Adversarial Examples for Random Convolutional Networks via Isoperimetric Inequalities on $\mathbb{so}(d)$

    cs.LG 2025-06 conditional novelty 7.0 of 10

    Using isoperimetric inequalities on SO(d), this paper proves that random convolutional networks with odd activations or ReLU have sign-flipping adversarial examples at distance O(||x0||/sqrt(d)).

  2. Robust learning of halfspaces under log-concave marginals

    cs.DS 2025-05 accept novelty 7.0 of 10

    An efficient agnostic learner for halfspaces over subgaussian isotropic log-concave distributions returns a classifier with error opt+O(ε) and boundary volume O(r+ε) in time d^{~O(1/ε^2)}.

  3. Adversarial Examples Are Not Bugs, They Are Superposition

    cs.LG 2025-08 unverdicted novelty 6.0 of 10

    The paper argues that adversarial examples arise from superposition, and shows that changing superposition changes robustness and vice versa in toy models and ResNet18.

  4. Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling

    cs.CV 2024-12 reject novelty 5.0 of 10

    Adversarial transferability in denoisers is attributed to Gaussian noise concentrating on a typical set, and a low-density Gaussian sampling defense (TS) is shown to improve robustness while preserving denoising accuracy.

  5. Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AI

    cs.CY 2026-07 accept novelty 4.0 of 10

    AI safety is a systems-governance problem: six recurring organizational failure patterns from past disasters remain unlearned in AI development, so component-level fixes like benchmarks and alignment cannot deliver safety.

  6. Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores

    cs.CR 2025-05 conditional novelty 4.0 of 10

    Adversarial patches can disrupt YOLOv5 and Faster R-CNN detectors in a simulated unmanned store, with a new histogram loss yielding small success-rate gains.

Pith tools