Pith. sign in

REVIEW 6 cited by

Unrestricted Adversarial Examples

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 1809.08352 v1 pith:FTGMR7HW submitted 2018-09-22 stat.ML cs.CVcs.LG

Tom B. Brown , Nicholas Carlini , Chiyuan Zhang , Catherine Olsson , Paul Christiano , Ian Goodfellow This is my paper · ORCID
classification stat.MLcs.CVcs.LG
keywords adversarialcontestlearningmachineadversarieshighinputsmodels
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to unconstrained adversaries. Defenders submit machine learning models, and try to achieve high accuracy and coverage on non-adversarial data while making no confident mistakes on adversarial inputs. Attackers try to subvert defenses by finding arbitrary unambiguous inputs where the model assigns an incorrect label with high confidence. We propose a simple unambiguous dataset ("bird-or- bicycle") to use as part of this contest. We hope this contest will help to more comprehensively evaluate the worst-case adversarial risk of machine learning models.

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. Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks

    cs.SD 2026-06 unverdicted novelty 6.0 of 10

    A conditional generator operating in neural audio codec latent space produces targeted adversarial audio examples in one forward pass, reaching up to 99% success rate at sub-7 ms inference.

  2. Position: Adversarial ML for LLMs Is Not Making Any Progress

    cs.LG 2025-02 conditional novelty 6.0 of 10

    The authors argue that LLM-era adversarial machine learning is less well-defined, harder to solve, and harder to evaluate, so meaningful progress may not be achievable or trackable in the current paradigm.

  3. Generalizability vs. Counterfactual Explainability Trade-Off

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A geometric probability called epsilon-VCP rises as models overfit, and the paper offers it as a label-free overfitting diagnostic.

  4. Developing Creative AI to Generate Sculptural Objects

    cs.LG 2019-08 conditional novelty 5.0 of 10

    ADD and PDD generate 3D point-cloud sculptures by applying DeepDream-style gradient updates to trained classifiers and amalgamating or partitioning point clouds to avoid sparsity.

  5. VENOM: Text-driven Unrestricted Adversarial Example Generation with Diffusion Models

    cs.CV 2025-01 conditional novelty 4.0 of 10

    A text-to-image diffusion attack that interleaves denoising with momentum-based adversarial gradients and an adaptive on/off switch to generate natural-looking unrestricted adversarial examples.

  6. Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation

    cs.CV 2024-11 conditional novelty 4.0 of 10

    A black-box face recognition attack that augments surrogate models with diverse parameter initializations and hard-model feature perturbations, achieving higher transferability.

Pith tools