Cover Image

From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gao, Yansong, Peng, Huaibing, Ma, Hua, Dai, Zhiyang, Wang, Shuo, Hu, Hongsheng, Fu, Anmin, Xue, Minhui
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
by: Fu, Anmin, et al.
Published: (2025)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
by: Li, Na, et al.
Published: (2025)

Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning
by: Hu, Hongsheng, et al.
Published: (2024)

Decaf: Data Distribution Decompose Attack against Federated Learning
by: Dai, Zhiyang, et al.
Published: (2024)

TruVRF: Towards Triple-Granularity Verification on Machine Unlearning
by: Zhou, Chunyi, et al.
Published: (2024)

Intellectual Property Protection for Deep Learning Model and Dataset Intelligence
by: Jiang, Yongqi, et al.
Published: (2024)

Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning
by: Dai, Zhiyang, et al.
Published: (2026)

Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
by: Ma, Hua, et al.
Published: (2023)

ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders
by: Jiang, Yongqi, et al.
Published: (2026)

Empowering IoT Firmware Secure Update with Customization Rights
by: Chen, Weihao, et al.
Published: (2025)

A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services
by: Hu, Hongsheng, et al.
Published: (2023)

50 Shades of Deceptive Patterns: A Unified Taxonomy, Multimodal Detection, and Security Implications
by: Shi, Zewei, et al.
Published: (2025)

Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification
by: Wang, Hanrui, et al.
Published: (2024)

Provably Unlearnable Data Examples
by: Wang, Derui, et al.
Published: (2024)

Detecting Adversarial Examples
by: Mumcu, Furkan, et al.
Published: (2024)

Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting
by: Ma, Hua, et al.
Published: (2025)

Adversarial Example Based Fingerprinting for Robust Copyright Protection in Split Learning
by: Lin, Zhangting, et al.
Published: (2025)

NeuroTrace: Inference Provenance-Based Detection of Adversarial Examples
by: Hmida, Firas Ben, et al.
Published: (2026)

Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples
by: Han, Sicong, et al.
Published: (2025)

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives
by: Wang, Nan, et al.
Published: (2025)

Isolate Trigger: Detecting and Eliminating Adaptive Backdoor Attacks
by: Sun, Chengrui, et al.
Published: (2025)

NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification
by: Nguyen, David D., et al.
Published: (2026)

Masked Language Model Based Textual Adversarial Example Detection
by: Zhang, Xiaomei, et al.
Published: (2023)

Position: Towards Resilience Against Adversarial Examples
by: Dai, Sihui, et al.
Published: (2024)

From Storage to Steering: Memory Control Flow Attacks on LLM Agents
by: Xu, Zhenlin, et al.
Published: (2026)

TEAM: Temporal Adversarial Examples Attack Model against Network Intrusion Detection System Applied to RNN
by: Liu, Ziyi, et al.
Published: (2024)

NCCR: to Evaluate the Robustness of Neural Networks and Adversarial Examples
by: Pu, Shi, et al.
Published: (2025)

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
by: Li, Na, et al.
Published: (2024)

BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning
by: Lu, Bingguang, et al.
Published: (2025)

DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks
by: Park, Seonhye, et al.
Published: (2022)

Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World
by: Ma, Hua, et al.
Published: (2025)

Effectiveness of Adversarial Benign and Malware Examples in Evasion and Poisoning Attacks
by: Kozák, Matouš, et al.
Published: (2025)

Transferability Ranking of Adversarial Examples
by: Levy, Mosh, et al.
Published: (2022)

DeepiSign-G: Generic Watermark to Stamp Hidden DNN Parameters for Self-contained Tracking
by: Abuadbba, Alsharif, et al.
Published: (2024)

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
by: Xue, Jing, et al.
Published: (2025)

Evasive Ransomware Attacks Using Low-level Behavioral Adversarial Examples
by: Hirano, Manabu, et al.
Published: (2025)

Obfuscating IoT Device Scanning Activity via Adversarial Example Generation
by: Li, Haocong, et al.
Published: (2024)

ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation
by: Liu, Ruixuan, et al.
Published: (2024)

Creating Valid Adversarial Examples of Malware
by: Kozák, Matouš, et al.
Published: (2023)

Laundering AI Authority with Adversarial Examples
by: Zhang, Jie, et al.
Published: (2026)