arXiv subjects

Haomiao Yang

Publications and source records attributed to Haomiao Yang.

8 recordsLinked to original sources

arXiv2026

Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP Backdoors

Contrastive Language-Image Pre-training models are widely reused across downstream interfaces, including feature extraction, retrieval, reranking, and selection. Existing CLIP backdoor, however, usually validate attacks on a small attack-native task, leaving unclear whether the same poisoned checkpoint remains exposed, weakens, or becomes not applicable when reused through other interfaces. We introduce DIFE, a Deployment-Interface Footprint Evaluation framework that audits backdoored CLIP checkpoints across deployment interfaces. DIFE makes various evaluations comparable by specifying each interface's component readout, trigger channel, target event, reference condition, and metric. DIFE also introduces effective-footprint diagnosis to identify the reusable CLIP component or component combination that carries exposure and explains where risk transfers. Auditing reproduced CLIP backdoors with DIFE reveals a structured landscape: native success is not a checkpoint-level risk certificate, exposure follows component footprints, text-side poisoning does not yield textual-encoder control, and some coupled attacks remain mechanism-bound. This audit reveals a import gapin existing CLIP backdoors: a textual encoder that itself becomes a reusable carrier of adversarial behavior. We therefore introduce BadTextTower to fill this gap. BadTextTower produces strong text-conditioned retrieval, reranking, and selection exposure while leaving visual-only reuse nearly clean.

cs.CR↗

arXiv2026

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models

Backdoor attacks against pre-trained models (PTMs) have traditionally operated under an ``immediacy assumption,'' where malicious behavior manifests instantly upon trigger occurrence. This work revisits and challenges this paradigm by introducing \textit{\textbf{Delayed Backdoor Attacks (DBA)}}, a new class of threats in which activation is temporally decoupled from trigger exposure. We propose that this \textbf{temporal dimension} is the key to unlocking a previously infeasible class of attacks: those that use common, everyday words as triggers. To examine the feasibility of this paradigm, we design and implement a proof-of-concept prototype, termed \underline{D}elayed Backdoor Attacks Based on \underline{N}onlinear \underline{D}ecay (DND). DND embeds a lightweight, stateful logic module that postpones activation until a configurable threshold is reached, producing a distinct latency phase followed by a controlled outbreak. We derive a formal model to characterize this latency behavior and propose a dual-metric evaluation framework (ASR and ASR$_{delay}$) to empirically measure the delay effect. Extensive experiments on four (natural language processing)NLP benchmarks validate the core capabilities of DND: it remains dormant for a controllable duration, sustains high clean accuracy ($\ge$94\%), and achieves near-perfect post-activation attack success rates ($\approx$99\%, The average of other methods is below 95\%.). Moreover, DND exhibits resilience against several state-of-the-art defenses. This study provides the first empirical evidence that the temporal dimension constitutes a viable yet unprotected attack surface in PTMs, underscoring the need for next-generation, stateful, and time-aware defense mechanisms.

cs.CR↗

arXiv2025

BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting

Multivariate long-term time series forecasting (MLTSF) models are increasingly deployed in critical domains such as climate, finance, and transportation. Despite their growing importance, the security of MLTSF models against backdoor attacks remains entirely unexplored. To bridge this gap, we propose BadTime, the first effective backdoor attack tailored for MLTSF. BadTime can manipulate hundreds of future predictions toward a target pattern by injecting a subtle trigger. BadTime addresses two key challenges that arise uniquely in MLTSF: (i) the rapid dilution of local triggers over long horizons, and (ii) the extreme sparsity of backdoor signals under stealth constraints. To counter dilution, BadTime leverages inter-variable correlations, temporal lags, and data-driven initialization to design a distributed, lag-aware trigger that ensures effective influence over long-range forecasts. To overcome sparsity, it introduces a hybrid strategy to select valuable poisoned samples and a decoupled backdoor training objective that adaptively adjusts the model's focus on the sparse backdoor signal, ensuring reliable learning at a poisoning rate as low as 1%. Extensive experiments show that BadTime significantly outperforms state-of-the-art (SOTA) backdoor attacks on time series forecasting by extending the attackable horizon from at most 12 timesteps to 720 timesteps (a 60-fold improvement), reducing MAE by over 50% on target variables, and boosting stealthiness by more than 3-fold under anomaly detection.

cs.CR↗

arXiv2025

The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning

In Federated Learning (FL), clients share gradients with a central server while keeping their data local. However, malicious servers could deliberately manipulate the models to reconstruct clients' data from shared gradients, posing significant privacy risks. Although such active gradient leakage attacks (AGLAs) have been widely studied, they suffer from two severe limitations: (i) coverage: no existing AGLAs can reconstruct all samples in a batch from the shared gradients; (ii) stealthiness: no existing AGLAs can evade principled checks of clients. In this paper, we address these limitations with two core contributions. First, we introduce a new theoretical analysis approach, which uniformly models AGLAs as backdoor poisoning. This analysis approach reveals that the core principle of AGLAs is to bias the gradient space to prioritize the reconstruction of a small subset of samples while sacrificing the majority, which theoretically explains the above limitations of existing AGLAs. Second, we propose Enhanced Gradient Global Vulnerability (EGGV), the first AGLA that achieves complete attack coverage while evading client-side detection. In particular, EGGV employs a gradient projector and a jointly optimized discriminator to assess gradient vulnerability, steering the gradient space toward the point most prone to data leakage. Extensive experiments show that EGGV achieves complete attack coverage and surpasses state-of-the-art (SOTA) with at least a 43% increase in reconstruction quality (PSNR) and a 45% improvement in stealthiness (D-SNR).

cs.CR↗

arXiv2024

Combinational Backdoor Attack against Customized Text-to-Image Models

Recently, Text-to-Image (T2I) synthesis technology has made tremendous strides. Numerous representative T2I models have emerged and achieved promising application outcomes, such as DALL-E, Stable Diffusion, Imagen, etc. In practice, it has become increasingly popular for model developers to selectively adopt personalized pre-trained text encoders and conditional diffusion models from third-party platforms, integrating them together to build customized (personalized) T2I models. However, such an adoption approach is vulnerable to backdoor attacks. In this work, we propose a \textbf{C}ombinational \textbf{B}ackdoor \textbf{A}ttack against \textbf{C}ustomized \textbf{T2I} models (CBACT2I) targeting this application scenario. Different from previous backdoor attacks against T2I models, CBACT2I embeds the backdoor into the text encoder and the conditional diffusion model separately. The customized T2I model exhibits backdoor behaviors only when the backdoor text encoder is used in combination with the backdoor conditional diffusion model. These properties make CBACT2I more stealthy and controllable than prior backdoor attacks against T2I models. Extensive experiments demonstrate the high effectiveness of CBACT2I with different backdoor triggers and backdoor targets, the strong generality on different combinations of customized text encoders and diffusion models, as well as the high stealthiness against state-of-the-art backdoor detection methods.

cs.CR↗

arXiv2024

DDFAD: Dataset Distillation Framework for Audio Data

Deep neural networks (DNNs) have achieved significant success in numerous applications. The remarkable performance of DNNs is largely attributed to the availability of massive, high-quality training datasets. However, processing such massive training data requires huge computational and storage resources. Dataset distillation is a promising solution to this problem, offering the capability to compress a large dataset into a smaller distilled dataset. The model trained on the distilled dataset can achieve comparable performance to the model trained on the whole dataset. While dataset distillation has been demonstrated in image data, none have explored dataset distillation for audio data. In this work, for the first time, we propose a Dataset Distillation Framework for Audio Data (DDFAD). Specifically, we first propose the Fused Differential MFCC (FD-MFCC) as extracted features for audio data. After that, the FD-MFCC is distilled through the matching training trajectory distillation method. Finally, we propose an audio signal reconstruction algorithm based on the Griffin-Lim Algorithm to reconstruct the audio signal from the distilled FD-MFCC. Extensive experiments demonstrate the effectiveness of DDFAD on various audio datasets. In addition, we show that DDFAD has promising application prospects in many applications, such as continual learning and neural architecture search.

cs.SD↗

arXiv2023

A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networks

The Large Language Models (LLMs) are poised to offer efficient and intelligent services for future mobile communication networks, owing to their exceptional capabilities in language comprehension and generation. However, the extremely high data and computational resource requirements for the performance of LLMs compel developers to resort to outsourcing training or utilizing third-party data and computing resources. These strategies may expose the model within the network to maliciously manipulated training data and processing, providing an opportunity for attackers to embed a hidden backdoor into the model, termed a backdoor attack. Backdoor attack in LLMs refers to embedding a hidden backdoor in LLMs that causes the model to perform normally on benign samples but exhibit degraded performance on poisoned ones. This issue is particularly concerning within communication networks where reliability and security are paramount. Despite the extensive research on backdoor attacks, there remains a lack of in-depth exploration specifically within the context of LLMs employed in communication networks, and a systematic review of such attacks is currently absent. In this survey, we systematically propose a taxonomy of backdoor attacks in LLMs as used in communication networks, dividing them into four major categories: input-triggered, prompt-triggered, instruction-triggered, and demonstration-triggered attacks. Furthermore, we conduct a comprehensive analysis of the benchmark datasets. Finally, we identify potential problems and open challenges, offering valuable insights into future research directions for enhancing the security and integrity of LLMs in communication networks.

cs.CR↗

arXiv2020

Private, Fair, and Verifiable Aggregate Statistics for Mobile Crowdsensing in Blockchain Era

In this paper, we propose FairCrowd, a private, fair, and verifiable framework for aggregate statistics in mobile crowdsensing based on the public blockchain. In specific, mobile users are incentivized to collect and share private data values (e.g., current locations) to fufill a commonly interested task released by a customer, and the crowdsensing server computes aggregate statistics over the values of mobile users (e.g., the most popular location) for the customer. By utilizing the ElGamal encryption, the server learns nearly nothing about the private data or the statistical result. The correctness of aggregate statistics can be publicly verified by using a new efficient and verifiable computation approach. Moreover, the fairness of incentive is guaranteed based on the public blockchain in the presence of greedy service provider, customers, and mobile users, who may launch payment-escaping, payment-reduction, free-riding, double-reporting, and Sybil attacks to corrupt reward distribution. Finally, FairCrowd is proved to achieve verifiable aggregate statistics with privacy preservation for mobile users. Extensive experiments are conducted to demonstrate the high efficiency of FairCrowd for aggregate statistics in mobile crowdsensing.

cs.CR↗