MétaCan
Menu
Back to cohort

Noise as a Double-Edged Sword: Reinforcement Learning Exploits Randomized Defenses in Neural Networks

2024· article· en· W4406460297 on OpenAlex
Steve Bakos, Pooria Madani, Heidar Davoudi

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsOntario Tech University
Fundersnot available
KeywordsSWORDReinforcement learningExploitComputer scienceNoise (video)Artificial neural networkArtificial intelligenceComputer securityWorld Wide WebImage (mathematics)

Abstract

fetched live from OpenAlex

This study investigates a counterintuitive phenomenon in adversarial machine learning: the potential for noise-based defenses to inadvertently aid evasion attacks in certain scenarios. While randomness is often employed as a defensive strategy against adversarial examples, our research reveals that this approach can sometimes backfire, particularly when facing adaptive attackers using reinforcement learning (RL). Our findings show that in specific cases, especially with visually noisy classes, the introduction of noise in the classifier’s confidence values can be exploited by the RL attacker, leading to a significant increase in evasion success rates. In some instances, the noise-based defense scenario outperformed other strategies by up to 20% on a subset of classes. However, this effect was not consistent across all classifiers tested, highlighting the complexity of the interaction between noise-based defenses and different models. These results suggest that in some cases, noise-based defenses can inadvertently create an adversarial training loop beneficial to the RL attacker. Our study emphasizes the need for a more nuanced approach to defensive strategies in adversarial machine learning, particularly in safety-critical applications. It challenges the assumption that randomness universally enhances defense against evasion attacks and highlights the importance of considering adaptive, RL-based attackers when designing robust defense mechanisms.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.973
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.015
GPT teacher head0.274
Teacher spread0.259 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it