This work characterizes the complementary relationship between reconstruction-based and robustness-based paradigms in the accuracy–efficiency design space under the evaluated conditions: the former suits compute-unconstrained scenarios while the latter serves latency-constrained deployments.
Abstract
Adversarial patch attacks pose a tangible physical-world threat to traffic sign recognition in autonomous driving systems. Current state-of-the-art defenses based on image reconstruction require dual-model deployment and add per-frame inference latency, making them impractical for resource-constrained embedded platforms such as mass-produced ADAS systems and aftermarket dashcams. This paper proposes a two-component defense that separates detection from mitigation. PatchGuard-Freq leverages frequency-domain analysis to detect attacked images with high accuracy, while adversarial fine-tuning enables the detector to recover most of its detection performance under attack without adding any inference module or architectural change. Experimental results show that the approach is effective in the latency regime targeted by this study: on the evaluated stop-sign and nine-class LISA benchmarks, under the evaluated detection placement (a fresh 110×110 patch at a uniformly random position), the detector achieves AUC = 1.0 with zero false positives across all four dataset configurations and all combined frequency variants, while the frequency-only arm of the ablation separates the data only where the patch covers almost the entire input, and adversarial fine-tuning recovers attacked mAP@0.5 on the COCO stop-sign test set from 19.4% to 68.4% on the 110×110-patch configuration while degrading clean mAP by only about 0.7 points. We further show that PatchGuard-Freq is vulnerable to adaptive (defense-aware) attacks and introduce defense-aware training that restores detection of such attacks to 100% without increasing false alarms. This work characterizes the complementary relationship between reconstruction-based and robustness-based paradigms in the accuracy–efficiency design space under the evaluated conditions: the former suits compute-unconstrained scenarios while the latter serves latency-constrained deployments. All quantitative results were obtained on desktop-grade GPUs; embedded-platform latency, memory, and energy were not measured, and the embedded discussion is limited to hardware-independent parameter and FLOP counts.
Backdoor as Probe is proposed, a test-time adversarial defense for CLIP that improves average robust accuracy from 1.0\% to 52.3\% while retaining clean accuracy, achieving performance comparable to state-of-the-art methods with up to a \(5.7\times\) inference speedup.
Zhong Ling Wang, Jie Zhang, Sen Nie et al.· 0 citations
AdROD outperforms five baseline defenses and exhibits superior generalizability compared with the evaluated adversarial-training baselines, while maintaining real-time performance for safely stopping the vehicle at a stop sign instrumented with adversarial patches.
Yuting Wu, Dongfang Guo, Xiangzhong Luo et al.· 0 citations
Universal serial bus (USB) human interface devices remain vulnerable to adversarial keystroke injection attacks because host systems implicitly trust connected peripherals. Recent poisoning and evasion attacks further reduce detection reliability by mimicking benign human typing patterns, creating overlapping benign an...
Chillara Anil Kumar, Ishan Barpanda, Paresh Saxena et al.· IEEE Transactions on Reliabi...· 0 citations
This survey unifies a fragmented literature spanning perception pipelines, input-adaptive neural inference, input-adaptive neural inference, and autoregressive and agentic systems and provides a threat-model taxonomy, consolidated quantitative comparisons, a defense review by control mechanism, and open challenges such...
This paper proposes a methodology for crafting principled frequency-based adversarial attacks, via a dedicated optimization framework, and proves that the attacks emerge as weighted $\ell_2$-projections onto this set, yielding a general and controlled attack generation mechanism.
Vicky Kouni, Stelios Perrakis, Francis R. Bach et al.· arXiv.org· 0 citations
CLIPGuard is proposed, a lightweight and fully black-box defense specifically designed to mitigate embedding-space backdoors in CLIP encoders, consistently outperforming existing black-box defenses, including CleanCLIP and CleanerCLIP.
A. Abdel-Naby, Mohamed Elmahallawy· Pacific-Asia Conference on K...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.