Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors

• URL: http://arxiv.org/abs/2608.00566v1
• Date: Sat, 01 Aug 2026 10:03:14 GMT
• Title: Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors
• Abstract summary: Post-hoc model explainers are widely deployed to audit models in high-stakes sensitive domains.<n>A few studies have examined potential attacks in the explainability pipeline.<n>We introduce a more potent white-box, gradient-regularized evasion attack framework.
• Score: 4.377640147713394
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare. This ensures the model's transparency and acceptability. However, a few studies have examined potential attacks in the explainability pipeline. Adversaries can attempt to conceal algorithmic biases or backdoors using adversarial explanation attacks. These attacks have relied on scaffolding out-of-distribution (OOD) detectors that toggle predictions when queried by an explainer. Consequently, defenses have been developed to successfully neutralize these black-box attacks by identifying their anomalous perturbation footprints. In this paper, we demonstrate a critical vulnerability by introducing a more potent white-box, gradient-regularized evasion attack framework. By employing a continuous-embedding dual-penalty framework, we directly penalize trigger feature gradients during training on in-distribution data. Since our approach embeds the evasion logic natively into the model parameters, without relying on OOD scaffolding wrappers, it generates smooth, in-distribution predictions that leave no anomaly footprint. Empirical evaluations across four benchmark tabular datasets (COMPAS, German Credit, IEEE-CIS, and Communities & Crime) confirm that our method systematically crushes target feature attribution to near-zero (<0.02), maintains >90% Attack Success Rates, and fundamentally bypasses Conditional Anomaly Detection.

Related papers

• AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation [48.55515767840701]
  "AI slop" is artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports.<n>This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage.
  arXiv  Detail & Related papers  (2026-08-26T11:48:38Z)
• SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense [77.70598852234149]
  Text-to-Video (T2V) generative models are vulnerable to jailbreak attacks in real-world deployment.<n>We propose SafeCA, a feature-level defense mechanism for safe cross-attention localization and regularization.<n> Experimental results show that SafeCA reduces the jailbreak success rate by about 20% on mainstream T2V models.
  arXiv  Detail & Related papers  (2026-08-11T14:01:24Z)
• Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trust [4.5294318938213465]
  Federated Learning (FL) is highly susceptible to stealthy backdoor attacks.<n>We identify a fundamental vulnerability termed Late-stage Failure''<n>We propose Secure-CHG, a hybrid framework that pivots the defense paradigm from morphological detection toward intrinsic semantic contribution verification.
  arXiv  Detail & Related papers  (2026-06-30T02:53:16Z)
• TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models [19.148124494194317]
  We propose TraceGuard, a process-guided security framework that transforms small-scale models into robust reasoning firewalls.<n>Our approach treats the reasoning trace as an untrusted payload and establishes a defense-in-depth strategy.<n>We demonstrate robustness against adaptive adversaries in a grey-box setting, establishing TraceGuard as a viable, low-latency security primitive.
  arXiv  Detail & Related papers  (2026-03-02T22:19:13Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models [56.09354775405601]
  Model extraction attacks aim to replicate the functionality of a black-box model through query access.<n>Most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt suspicious inputs.<n>We propose MISLEADER, a novel defense strategy that does not rely on OOD assumptions.
  arXiv  Detail & Related papers  (2025-06-03T01:37:09Z)
• Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation [95.3977252782181]
  Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions.<n>We introduce a novel training paradigm aimed at enhancing robustness against transferable adversarial examples (TAEs) in a more efficient and effective way.
  arXiv  Detail & Related papers  (2025-04-20T09:07:10Z)
• Indiscriminate Disruption of Conditional Inference on Multivariate Gaussians [60.22542847840578]
  Despite advances in adversarial machine learning, inference for Gaussian models in the presence of an adversary is notably understudied. We consider a self-interested attacker who wishes to disrupt a decisionmaker's conditional inference and subsequent actions by corrupting a set of evidentiary variables. To avoid detection, the attacker also desires the attack to appear plausible wherein plausibility is determined by the density of the corrupted evidence.
  arXiv  Detail & Related papers  (2024-11-21T17:46:55Z)
• BadGD: A unified data-centric framework to identify gradient descent vulnerabilities [10.996626204702189]
  BadGD sets a new standard for understanding and mitigating adversarial manipulations. This research underscores the severe threats posed by such data-centric attacks and highlights the urgent need for robust defenses in machine learning.
  arXiv  Detail & Related papers  (2024-05-24T23:39:45Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• DALA: A Distribution-Aware LoRA-Based Adversarial Attack against Language Models [64.79319733514266]
  Adversarial attacks can introduce subtle perturbations to input data. Recent attack methods can achieve a relatively high attack success rate (ASR) We propose a Distribution-Aware LoRA-based Adversarial Attack (DALA) method.
  arXiv  Detail & Related papers  (2023-11-14T23:43:47Z)
• Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification [31.38942054994932]
  Federated Learning (FL) systems are susceptible to adversarial attacks.<n>RedJasper is a two-staged anomaly detection method specifically designed for real-world FL deployments.<n>It identifies suspicious activities in the first stage, then activates the second stage conditionally to further scrutinize the suspicious local models.
  arXiv  Detail & Related papers  (2023-10-06T07:09:05Z)
• Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks [26.905553663353825]
  We offer a theoretical characterization of the trade-off between detection and false positive rates for stateful defenses. We analyze the impact of this trade-off on the convergence of black-box attacks.
  arXiv  Detail & Related papers  (2023-07-30T22:31:01Z)
• IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks [45.81957796169348]
  Backdoor attacks are an insidious security threat against machine learning models. We introduce IMBERT, which uses either gradients or self-attention scores derived from victim models to self-defend against backdoor attacks. Our empirical studies demonstrate that IMBERT can effectively identify up to 98.5% of inserted triggers.
  arXiv  Detail & Related papers  (2023-05-25T22:08:57Z)

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.