Poisoned Acoustics

• URL: http://arxiv.org/abs/2602.22258v1
• Date: Wed, 25 Feb 2026 01:09:43 GMT
• Title: Poisoned Acoustics
• Authors: Harrison Dahme,
• Abstract summary: Training-data poisoning attacks can induce targeted, undetectable failure in deep neural networks by corrupting a vanishingly small fraction of training labels.<n>We demonstrate this on acoustic vehicle classification using the MELAUDIS urban intersection dataset.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training-data poisoning attacks can induce targeted, undetectable failure in deep neural networks by corrupting a vanishingly small fraction of training labels. We demonstrate this on acoustic vehicle classification using the MELAUDIS urban intersection dataset (approx. 9,600 audio clips, 6 classes): a compact 2-D convolutional neural network (CNN) trained on log-mel spectrograms achieves 95.7% Attack Success Rate (ASR) -- the fraction of target-class test samples misclassified under the attack -- on a Truck-to-Car label-flipping attack at just p=0.5% corruption (48 records), with zero detectable change in aggregate accuracy (87.6% baseline; 95% CI: 88-100%, n=3 seeds). We prove this stealth is structural: the maximum accuracy drop from a complete targeted attack is bounded above by the minority class fraction (beta). For real-world class imbalances (Truck approx. 3%), this bound falls below training-run noise, making aggregate accuracy monitoring provably insufficient regardless of architecture or attack method. A companion backdoor trigger attack reveals a novel trigger-dominance collapse: when the target class is a dataset minority, the spectrogram patch trigger becomes functionally redundant--clean ASR equals triggered ASR, and the attack degenerates to pure label flipping. We formalize the ML training pipeline as an attack surface and propose a trust-minimized defense combining content-addressed artifact hashing, Merkle-tree dataset commitment, and post-quantum digital signatures (ML-DSA-65/CRYSTALS-Dilithium3, NIST FIPS 204) for cryptographically verifiable data provenance.

Related papers

• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Variance-Based Defense Against Blended Backdoor Attacks [0.0]
  Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models.<n>We propose a novel defense method that trains a model on the given dataset, detects poisoned classes, and extracts the critical part of the attack trigger.
  arXiv  Detail & Related papers  (2025-06-02T09:01:35Z)
• Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off [20.713624299599722]
  Semi-supervised learning (SSL) has achieved remarkable performance with a small fraction of labeled data.<n>This large pool of untrusted data is extremely vulnerable to data poisoning, leading to potential backdoor attacks.<n>We propose a novel method, Unlabeled Data Purification (UPure), to disrupt the association between trigger patterns and target classes.
  arXiv  Detail & Related papers  (2024-07-14T12:42:11Z)
• Learning and Certification under Instance-targeted Poisoning [49.55596073963654]
  We study PAC learnability and certification under instance-targeted poisoning attacks. We show that when the budget of the adversary scales sublinearly with the sample complexity, PAC learnability and certification are achievable. We empirically study the robustness of K nearest neighbour, logistic regression, multi-layer perceptron, and convolutional neural network on real data sets.
  arXiv  Detail & Related papers  (2021-05-18T17:48:15Z)
• Hidden Backdoor Attack against Semantic Segmentation Models [60.0327238844584]
  The emphbackdoor attack intends to embed hidden backdoors in deep neural networks (DNNs) by poisoning training data. We propose a novel attack paradigm, the emphfine-grained attack, where we treat the target label from the object-level instead of the image-level. Experiments show that the proposed methods can successfully attack semantic segmentation models by poisoning only a small proportion of training data.
  arXiv  Detail & Related papers  (2021-03-06T05:50:29Z)
• Mitigating the Impact of Adversarial Attacks in Very Deep Networks [10.555822166916705]
  Deep Neural Network (DNN) models have vulnerabilities related to security concerns. Data poisoning-enabled perturbation attacks are complex adversarial ones that inject false data into models. We propose an attack-agnostic-based defense method for mitigating their influence.
  arXiv  Detail & Related papers  (2020-12-08T21:25:44Z)
• How Robust are Randomized Smoothing based Defenses to Data Poisoning? [66.80663779176979]
  We present a previously unrecognized threat to robust machine learning models that highlights the importance of training-data quality. We propose a novel bilevel optimization-based data poisoning attack that degrades the robustness guarantees of certifiably robust classifiers. Our attack is effective even when the victim trains the models from scratch using state-of-the-art robust training methods.
  arXiv  Detail & Related papers  (2020-12-02T15:30:21Z)
• Mitigating Backdoor Attacks in Federated Learning [9.582197388445204]
  We propose a new and effective method to mitigate backdoor attacks after the training phase. Specifically, we design a federated pruning method to remove redundant neurons in the network and then adjust the model's extreme weight values. Experiments conducted on distributed Fashion-MNIST show that our method can reduce the average attack success rate from 99.7% to 1.9% with a 5.5% loss of test accuracy.
  arXiv  Detail & Related papers  (2020-10-28T18:39:28Z)
• Deep Partition Aggregation: Provable Defense against General Poisoning Attacks [136.79415677706612]
  Adrial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. We propose two novel provable defenses against poisoning attacks. DPA is a certified defense against a general poisoning threat model. SS-DPA is a certified defense against label-flipping attacks.
  arXiv  Detail & Related papers  (2020-06-26T03:16:31Z)
• Evading Deepfake-Image Detectors with White- and Black-Box Attacks [75.13740810603686]
  We show that a popular forensic approach trains a neural network to distinguish real from synthetic content. We develop five attack case studies on a state-of-the-art classifier that achieves an area under the ROC curve (AUC) of 0.95 on almost all existing image generators. We also develop a black-box attack that, with no access to the target classifier, reduces the AUC to 0.22.
  arXiv  Detail & Related papers  (2020-04-01T17:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.