Deepfake detectors are DUMB: A benchmark to assess adversarial training robustness under transferability constraints

• URL: http://arxiv.org/abs/2601.05986v1
• Date: Fri, 09 Jan 2026 18:06:19 GMT
• Title: Deepfake detectors are DUMB: A benchmark to assess adversarial training robustness under transferability constraints
• Authors: Adrian Serrano, Erwan Umlil, Ronan Thomas,
• Abstract summary: We extend the DUMB -- dataset soUrces, Model architecture and Balance - and DUMBer methodology to deepfake detection.<n>We evaluate robustness detectors against adversarial attacks under transferability constraints and cross-dataset configuration.<n>Experiments show that adversarial training strategies reinforce robustness in the in-distribution cases but can also degrade it under cross-dataset configuration depending on the strategy adopted.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deepfake detection systems deployed in real-world environments are subject to adversaries capable of crafting imperceptible perturbations that degrade model performance. While adversarial training is a widely adopted defense, its effectiveness under realistic conditions -- where attackers operate with limited knowledge and mismatched data distributions - remains underexplored. In this work, we extend the DUMB -- Dataset soUrces, Model architecture and Balance - and DUMBer methodology to deepfake detection. We evaluate detectors robustness against adversarial attacks under transferability constraints and cross-dataset configuration to extract real-world insights. Our study spans five state-of-the-art detectors (RECCE, SRM, XCeption, UCF, SPSL), three attacks (PGD, FGSM, FPBA), and two datasets (FaceForensics++ and Celeb-DF-V2). We analyze both attacker and defender perspectives mapping results to mismatch scenarios. Experiments show that adversarial training strategies reinforce robustness in the in-distribution cases but can also degrade it under cross-dataset configuration depending on the strategy adopted. These findings highlight the need for case-aware defense strategies in real-world applications exposed to adversarial attacks.

Related papers

• DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective [70.77570343385928]
  We introduce a novel taxonomy, classifying existing methods based on their reliance on internal features (IF) (inherent to the data) versus external features (EF) (artificially introduced for auditing)<n>We formulate two primary attack types: evasion attacks, designed to conceal the use of a dataset, and forgery attacks, intending to falsely implicate an unused dataset.<n>Building on the understanding of existing methods and attack objectives, we further propose systematic attack strategies: decoupling, removal, and detection for evasion; adversarial example-based methods for forgery.<n>Our benchmark, DATABench, comprises 17 evasion attacks, 5 forgery attacks, and 9
  arXiv  Detail & Related papers  (2025-07-08T03:07:15Z)
• Benchmarking Misuse Mitigation Against Covert Adversaries [80.74502950627736]
  Existing language model safety evaluations focus on overt attacks and low-stakes tasks.<n>We develop Benchmarks for Stateful Defenses (BSD), a data generation pipeline that automates evaluations of covert attacks and corresponding defenses.<n>Our evaluations indicate that decomposition attacks are effective misuse enablers, and highlight stateful defenses as a countermeasure.
  arXiv  Detail & Related papers  (2025-06-06T17:33:33Z)
• Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency [25.830427564563422]
  Class-Specific Anomaly Detection (CSAD) is an effective novel anomaly detection approach.<n> CSAD evaluates adversarial samples relative to their predicted class distribution, rather than a broad benign distribution.<n>Our evaluation incorporates both anomaly detection rates with SHAP-based assessments to provide a more comprehensive measure of adversarial sample quality.
  arXiv  Detail & Related papers  (2024-12-10T09:17:09Z)
• Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging [12.644923600594176]
  Adversarial attacks pose significant threats to the reliability and safety of deep learning models.<n>This paper introduces a novel framework that integrates conformal prediction with game-theoretic defensive strategies.
  arXiv  Detail & Related papers  (2024-11-07T02:20:04Z)
• FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defenses [50.921333548391345]
  Federated Learning is a privacy preserving decentralized machine learning paradigm.<n>Recent research has revealed that private ground truth data can be recovered through a gradient technique known as Deep Leakage.<n>This paper introduces the FEDLAD Framework (Federated Evaluation of Deep Leakage Attacks and Defenses), a comprehensive benchmark for evaluating Deep Leakage attacks and defenses.
  arXiv  Detail & Related papers  (2024-11-05T11:42:26Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• Exploring the Physical World Adversarial Robustness of Vehicle Detection [13.588120545886229]
  Adrial attacks can compromise the robustness of real-world detection models. We propose an innovative instant-level data generation pipeline using the CARLA simulator. Our findings highlight diverse model performances under adversarial conditions.
  arXiv  Detail & Related papers  (2023-08-07T11:09:12Z)
• Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations [55.2480439325792]
  Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. FL faces vulnerabilities such as poisoning attacks, undermining model integrity with both untargeted performance degradation and targeted backdoor attacks. We define a new notion of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. MESAS is the first defense robust against strong adaptive adversaries, effective in real-world data scenarios, with an average overhead of just 24.37 seconds.
  arXiv  Detail & Related papers  (2023-06-06T11:44:42Z)
• A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks [84.10546708708554]
  3D object detectors are increasingly crucial for security-critical tasks. It is imperative to understand their robustness against adversarial attacks. This paper presents the first comprehensive evaluation and analysis of the robustness of LiDAR-based 3D detectors under adversarial attacks.
  arXiv  Detail & Related papers  (2022-12-20T13:09:58Z)
• Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising [3.2023814100005907]
  Attacks manifesting as perturbations in the observation space managed by the external environment have been shown to downgrade policy performance. To defend against these attacks, we propose a novel defense strategy using a detect-and-denoise schema. Our solution does not require sampling data in an environment under attack, thereby greatly reducing risk during training.
  arXiv  Detail & Related papers  (2022-06-14T22:28:30Z)

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.