Huaibing Peng

Huaibing Peng

Auto-generated profile, based on publicly available information

Huaibing Peng

School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 January 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HPHuaibing Peng
Huaibing Peng
HQHuming Qiu
Huming Qiu
HMHua Ma
Hua Ma
SWShuo Wang
Shuo Wang
AFAnmin Fu
Anmin Fu
YGYansong Gao
Yansong Gao
Deep learning models with backdoors act maliciously when triggered but seem normal otherwise. This risk, often increased by model outsourcing, challenges their secure use. Although countermeasures exist, their defense against adaptive attacks is under-examined, possibly leading to security misjudgments. This study is the first intricate examination illustrating the difficulty of detecting backdoors in outsourced models, especially when attackers adjust their strategies, even if their capabilities are significantly limited. It is relatively straightforward for attackers to circumvent detection by trivially violating its threat model (e.g., using advanced backdoor types or trigger designs not covered by the detection). However, this research highlights that various leading detection defenses can simultaneously be evaded using simple adaptive strategies, even under their defined threat models and with limited adversary capabilities (e.g., using easily detectable triggers while maintaining a high attack success rate). To be more specific, this study introduces a novel methodology that employs trigger specificity enhancement and training regulation in a symbiotic manner. This approach allows us to evade multiple backdoor detection defenses simultaneously, including Neural Cleanse (Oakland 19’), ABS (CCS 19’), and MNTD (Oakland 21’). These were the detection tools selected for the Evasive Trojans Track of the 2022 NeurIPS Trojan Detection Challenge. Even when applied in conjunction with these defenses under stringent conditions, such as a high attack success rate (> 97%) and the restricted use of the simplest trigger (small white square), our straightforward method garnered the second prize in NeurIPS Trojan Detection Challenge. Notably, for the first time, our adaptive attack successfully evaded other recent state-of-the-art defenses, including FeatureRE (NeurIPS 22’) and Beatrix (NDSS 23’). This study suggests that existing model outsourcing backdoor defenses remain vulnerable to adaptive attacks, and thus, the use of third-party models should be avoided whenever possible.

3 July 2024 in Expert Systems with Applications
Verified
Journal Article
Open access
YZYifan Zhu
Yifan Zhu
HPHuaibing Peng
Huaibing Peng
AFAnmin Fu
Anmin Fu
WYWei Yang
Wei Yang
HMHua Ma
Hua Ma
YGYansong Gao
Yansong Gao

21 January 2026 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
YGYansong Gao
Yansong Gao
HPHuaibing Peng
Huaibing Peng
HMHua Ma
Hua Ma
ZDZhiyang Dai
Zhiyang Dai
SWShuo Wang
Shuo Wang
MXMinhui Xue
Minhui Xue
We unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies, which focus on spatial (or static) imprints within the targeted underlying victim models, we present a novel temporal paradigm for understanding these attacks. These imprints are encapsulated within a single loss metric, spanning universally across diverse tasks such as classification and regression, and modalities including image, text, and audio. Recognizing the distinct nature of loss between adversarial and clean examples, we exploit this temporal imprint for AE detection by proposing (Traceable Adversarial Temporal Imprints. TRAIT operates under minimal assumptions without prior knowledge of attacks, thereby framing the detection challenge as a one-class classification problem. However, detecting AEs is still challenged by significant overlaps between the constructed synthetic losses of adversarial and clean examples due to the absence of ground truth for incoming inputs. TRAIT addresses this challenge by converting the synthetic loss into a spectrum signature, using the technique of Fast Fourier Transform to highlight the discrepancies, drawing inspiration from the temporal nature of the imprints, analogous to time-series signals. Across 12 AE attacks including SMACK (USENIX Sec'2023), TRAIT demonstrates consistent outstanding performance across comprehensively evaluated modalities (image, text, audio), tasks (classification and regression), datasets (nine datasets), and model architectures (e.g., ResNeXt50, BERT, RoBERTa, AudioNet). In all scenarios, TRAIT achieves an AE detection accuracy exceeding 97%, often around 99%, while maintaining a false rejection rate of 1%. TRAIT remains effective under the formulated strong adaptive attacks.