Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs

• URL: http://arxiv.org/abs/2604.03843v1
• Date: Sat, 04 Apr 2026 19:50:04 GMT
• Title: Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs
• Abstract summary: This paper examines the vulnerability of a RoBERTa-based malware detector that linearizes control flow graphs into sequences of function calls.<n>By evaluating evasion strategies within this graph-to-sequence framework, we provide insight into the practical robustness of transformer-based malware detectors beyond aggregate detection accuracy.
• Score: 0.19116784879310025
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Transformer-based malware detection systems operating on graph modalities such as control flow graphs (CFGs) achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial evasion attacks remains underexplored. This paper examines the vulnerability of a RoBERTa-based malware detector that linearizes CFGs into sequences of function calls, a design choice that enables transformer modeling but may introduce token-level sensitivities and ordering artifacts exploitable by adversaries. By evaluating evasion strategies within this graph-to-sequence framework, we provide insight into the practical robustness of transformer-based malware detectors beyond aggregate detection accuracy. This paper proposes a white-box adversarial evasion attack that leverages explainability mechanisms to identify and perturb most influential graph components. Using token- and word-level attributions derived from integrated gradients, the attack iteratively replaces positively attributed function calls with synthetic external imports, producing adversarial CFG representations without altering overall program structure. Experimental evaluation on small- and large-scale Windows Portable Executable (PE) datasets demonstrates that the proposed method can reliably induce misclassification, even against models trained to high accuracy. Our results highlight that explainability tools, while valuable for interpretability, can also expose critical attack surfaces in transformer-based malware detectors.

Related papers

• Defending against Model Extraction for GNNs with Model Reprogramming [57.82196268649236]
  Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (ML)<n>Still, their black-box deployment exposes them to Model Extraction (ME) attacks.<n>Existing defenses suffer from a critical ''Euclidean bias''<n>We propose GraphRP, a proactive defense framework that repurposes Model Reprogramming for security.
  arXiv  Detail & Related papers  (2026-08-11T23:20:15Z)
• Transcoders for Investigating Deception in Language Models [0.0]
  We investigate the use of transcoders to analyse deceptive behaviour in language models.<n>We identify a dictionary of deception-related features that exert a stronger influence on deceptive outputs.
  arXiv  Detail & Related papers  (2026-07-16T10:10:10Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Backdoor Directions in Vision Transformers [56.382912038371046]
  This paper investigates how Backdoor Attacks are represented within Vision Transformers (ViTs)<n>We identify a specific trigger direction'' in the model's activations that corresponds to the internal representation of the trigger.<n>Using this direction as a diagnostic tool, we trace how backdoor features are processed across layers.
  arXiv  Detail & Related papers  (2026-03-11T14:13:48Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• NatGVD: Natural Adversarial Example Attack towards Graph-based Vulnerability Detection [0.259184846358882]
  This paper proposes NatGVD, a novel attack methodology that generates natural adversarial vulnerable code to circumvent GNN-based and graph-aware vulnerability detectors.<n>With extensive evaluation of NatGVD on state-of-the-art vulnerability detection systems, the results reveal up to 53.04% evasion rate across GNN-based detectors and graph-aware transformer-based detectors.
  arXiv  Detail & Related papers  (2025-10-06T16:24:19Z)
• ViSTR-GP: Online Cyberattack Detection via Vision-to-State Tensor Regression and Gaussian Processes in Automated Robotic Operations [5.95097350945477]
  Connected and automated factories face growing cybersecurity risks that can potentially cause interruptions and damages to physical operations.<n>Data-integrity attacks often involve sophisticated exploitation of vulnerabilities that enable an attacker to access and manipulate the operational data.<n>This paper develops an online detection framework, ViSTR-GP, that cross-checks encoder-reported measurements against a vision-based estimate from an overhead camera outside the controller's authority.
  arXiv  Detail & Related papers  (2025-09-13T19:10:35Z)
• MirGuard: Towards a Robust Provenance-based Intrusion Detection System Against Graph Manipulation Attacks [13.92935628832727]
  MirGuard is an anomaly detection framework that combines logic-aware multi-view augmentation with contrastive representation learning.<n>MirGuard significantly outperforms state-of-the-art detectors in robustness against various graph manipulation attacks.
  arXiv  Detail & Related papers  (2025-08-14T13:35:51Z)
• Learning-based Detection of GPS Spoofing Attack for Quadrotors [11.398843753130425]
  We present QUADFormer, an advanced attack detection framework for quadrotor UAVs leveraging a transformer-based architecture.<n>This framework features a residue generator that produces sequences sensitive to anomalies, which are then analyzed by the transformer to capture statistical patterns for detection and classification.
  arXiv  Detail & Related papers  (2025-01-10T02:20:59Z)
• Evaluating the Adversarial Robustness of Detection Transformers [4.3012765978447565]
  Despite the advancements in object detection transformers (DETRs), their robustness against adversarial attacks remains underexplored.<n>This paper presents a comprehensive evaluation of DETR model and its variants under both white-box and black-box adversarial attacks.<n>Our analysis reveals high intra-network transferability among DETR variants, but limited cross-network transferability to CNN-based models.
  arXiv  Detail & Related papers  (2024-12-25T00:31:10Z)
• A Hybrid Framework for Statistical Feature Selection and Image-Based Noise-Defect Detection [55.2480439325792]
  This paper presents a hybrid framework that integrates both statistical feature selection and classification techniques to improve defect detection accuracy.<n>We present around 55 distinguished features that are extracted from industrial images, which are then analyzed using statistical methods.<n>By integrating these methods with flexible machine learning applications, the proposed framework improves detection accuracy and reduces false positives and misclassifications.
  arXiv  Detail & Related papers  (2024-12-11T22:12:21Z)
• Graph Backdoor [53.70971502299977]
  We present GTA, the first backdoor attack on graph neural networks (GNNs) GTA departs in significant ways: it defines triggers as specific subgraphs, including both topological structures and descriptive features. It can be instantiated for both transductive (e.g., node classification) and inductive (e.g., graph classification) tasks.
  arXiv  Detail & Related papers  (2020-06-21T19:45:30Z)

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.