arXiv subjects

Qingqing Ye

Publications and source records attributed to Qingqing Ye.

At least 19 recordsLinked to original sources

arXiv2026

Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds

Machine unlearning aims to erase the influence of a designated forget set from a trained model while preserving strong utility on the retain set. Approximate unlearning methods efficiently achieve this goal without full retraining, but their effectiveness is primarily assessed using dataset-level aggregate metrics. These aggregate metrics can mask deviations from retraining at the level of individual samples. In this work, we focus on per-sample unlearning effectiveness. We introduce SALA (Sample-grained Likelihoods ALignment), a plug-in optimization framework that enables approximate unlearning methods to operate at the level of individual samples by steering each example toward its correct target distribution. To quantitatively assess this behavior, we further propose the sample-grained distribution gap, a metric that captures per-sample discrepancies between approximate unlearning and exact retraining output distributions. We provide theoretical guarantees showing that SALA contracts this gap and yields a bounded per-sample discrepancy to retraining. To make this framework practical, we develop a low-cost estimation method for the member and non-member target distributions. Extensive experiments on classification and generation tasks demonstrate that SALA reduces the sample-grained distribution gap by up to $86.67\%$ when paired with existing approximate unlearning baselines, while also improving robustness to unlearning hyperparameters.

cs.LG↗

arXiv2026

Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure

Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of the agent acting as a disruptive "hub" within the user-agent-service chain remains largely overlooked. In this work, we expose a novel threat paradigm by introducing Mobius Injection, a sophisticated attack that weaponizes autonomous agents into zombie nodes to launch what we define as Agent-based and -Oriented DDoS (AbO-DDoS) attacks. Mobius Injection composes known indirect prompt injection and persistent agent components through a distinct structural mechanism named Semantic Closure, which induces sustained recursive execution of agent components through a single injection event. We demonstrate that this attack is lightweight for the adversary, can evade traditional volumetric DDoS monitors and input filters calibrated for low false-positive rates, and is highly configurable, allowing for surgical targeting of specific environments or model providers. To evaluate the real-world impact, we conduct extensive experiments across three representative claw-style agents and three mainstream coding agents, integrated with 12 frontier proprietary or open-weight LLMs. Our results demonstrate that Mobius Injection achieves substantial attack success across diverse tasks, driving single-node call amplification up to 51.0x. Under coordinated multi-node pressure, each infected node still drains about 123k--127k tokens on a shared five-GPU backend; benign request latency rises by abou 23x--24x, and coordinated infections eventually saturate shared capacity until benign traffic is effectively denied service.

cs.CR↗

arXiv2026

Machine Unlearning in Low-Dimensional Feature Subspace

Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspective for MU is presented upon low-dimensional feature subspaces, which gives rise to the potentials of separating the remaining and forgetting data herein. This separability motivates our LOFT, a method that proceeds unlearning in a LOw-dimensional FeaTure subspace from the pretrained model through principal projections, which are optimized to maximally capture the information of the remaining data and meanwhile diminish that of the forgetting data. During unlearning, LOFT simply optimizes a small-size projection matrix that can be flexibly inserted into the pretrained model, requiring just one-shot feature fetching from the pretrained model. LOFT demonstrates that effective and efficient MU can be achieved in low-dimensional feature subspaces even without repeated raw-data access or updates to the entire pretrained model. Extensive experiments validate the significantly lower computational overhead and superior unlearning performance of LOFT across diverse models, datasets, tasks, and applications. Code is publicly available.

cs.LG↗

arXiv2026

SteerProbe: Learning to Bypass Safety Steering in Vision-Language Models

Activation steering offers an inference-time defense for vision--language models (VLMs) by modifying intermediate representations without updating backbone parameters. However, protection on benchmark inputs may not persist across alternative expressions of the same harmful request. We investigate this gap using fixed textual, visual, and joint reformulations designed to preserve the underlying intent, and find that these changes can bypass representative steering defenses. A complementary local analysis provides a sufficient condition under which a reformulation can cross a surrogate safety margin despite any admissible change in the local steering correction. We then introduce SteerProbe, an output-only black-box attack that learns to select effective reformulations for unseen requests from a shared calibration budget. Across three VLM backbones, two benchmarks, and three steering defenses, SteerProbe increases Harmful Rate in all defended settings using 500 total calibration queries per endpoint and benchmark, raising the average from 7.43% to 18.36%. These findings highlight that robustness on original benchmark inputs is insufficient to characterize the safety of steering defenses and motivate reformulation robustness as an important evaluation dimension. They further motivate steering mechanisms that preserve safety across intent-preserving multimodal variations while maintaining benign utility.

cs.CR↗

arXiv2026

DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections

As GUI-based mobile agents rapidly progress, rigorous safety evaluation of their autonomous decision-making in realistic app interfaces becomes increasingly critical. Existing benchmarks mainly focus on execution-level anomalies using task success or hijack rates, but fail to capture the in-task goal deviation risk in multi-candidate selection tasks, where the decision may be steered toward an attacker-specified target, even in violation of instruction-implied constraints (e.g., cheapest/highest-rated), without any overt execution anomalies. We present DIBench, a decision integrity benchmark for measuring this risk in mobile agents. DIBench covers 7 commercial and 3 simulated apps with 5 task types. Under a threat model restricted to non-privileged UI content, we construct 8 deceptive injection probe instantiations that can steer critical selections without overt anomalies. The benchmark includes 1,000 clean and 36,672 injected instances, with a unified protocol and integrity metrics for comparison. Experiments spanning 4 agent frameworks and 7 base models show that completion-based evaluation can overestimate agent trustworthiness and miss decision-integrity risks: deceptive injections steer selections and shift early action policies, inflating completion rates and creating a misleading illusion of safety. Common defenses, including detection, image preprocessing, and prompt reminders, yield inconsistent integrity gains. Overall, DIBench provides a unified, reproducible benchmark to quantify the risk of in-task goal deviation in mobile agents and enable comparable evaluations of safety defenses.

cs.CR↗

arXiv2026

SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents

Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that task-, attack-, or choice-based evaluations may miss. We study functional counterfeits: implementations that match benign alternatives on the requested output but add an effect forbidden by the task contract. We introduce SINGED (Source Integrity and the Nonidentifiability Gap in Execution Decisions for LLM Agents), a controlled benchmark covering five primary and two held-out task families. It varies displayed rank, evidence depth, decision policy, model release, and agent configuration, while task and process oracles verify the artifact and execution path. Across 7,549 audited trials, the randomized-rank study finds counterfeit execution in 45% (27/60) of rank-one trials and none at later ranks. Cross-candidate comparison eliminates shallow failures and reduces layered failures from 15.7% to 4.2%, but leaves dependency failures; its benefit is uncertain on unseen effects and public-package structures. Moreover, seven releases with no counterfeit executions when benign alternatives are available execute the counterfeit in 55/175 single-source cells after alternatives are removed. SINGED thus exposes a rank-, evidence-, and choice-sensitive outcome-to-execution gap: evaluation must connect correct outputs to execution paths.

cs.CR↗

arXiv2026

Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions

Machine unlearning aims to remove target influence while preserving other capabilities. This survey compares methods, benchmarks, and evidence across large language models and systems using retrieval, memory, tools, and interacting agents. A five-layer framework connects removal requests, system boundaries, target locations, interventions, and supported claims. A seven-stage lifecycle and six evidence dimensions guide comparison. The review shows that target construction, retained data, and recovery tests affect reported outcomes. Evidence from model evaluations remains insufficient to establish removal across external state and subsequent updates, motivating evaluation that tracks dependencies and tests whether target influence returns.

cs.CR↗

arXiv2026

FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models

Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of a target individual. A common countermeasure is to embed imperceptible, low-energy watermarks, yet recent studies show these signatures are brittle: modest post-processing or lightweight adversarial perturbations readily suppress detection, exposing a fundamental tension between imperceptibility and robustness. We introduce FeatMark, a watermarking framework that shifts from pixel-level, energy-starved perturbations to inconspicuous semantic features: small, scene-consistent micro-features that remain natural to humans while providing a stronger, machine-verifiable provenance signal. FeatMark builds domain-specific feature banks that encode each watermark as a compact concept program, pairing open-vocabulary semantic cues with reliable edit regions and instruction templates. It then automatically selects features that are both feasible and executable and injects them through modular, mask-guided concept editing, yielding highly localized, scene-consistent micro-edits that are difficult to perceive. We conduct extensive experiments across VGGFace2, CelebA-HQ, and WikiArt, evaluating against 10 strong watermark removal/purification attacks (including regeneration-style purification) and several bespoke adaptive attacks tailored to FeatMark, to assess perceptual fidelity, watermark detection accuracy, and robustness. We further demonstrate FeatMark's extensibility to video mimicry attacks. The results show FeatMark remains virtually impervious, withstanding all evaluated attacks with negligible bit-accuracy and fidelity degradation.

cs.CR↗

arXiv2026

TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement

Multimodal training relies on image-text corpora collected from external sources, creating opportunities for attackers to poison the data. Stealthy attacks can preserve plausible image-text pairs while concealing the differences used by detectors, so apparently clean data can still redirect the trained model. We therefore ask which properties a poison set must preserve for the attack to remain effective. A small poison set must still exert enough collective influence during training to induce the attacker's target behavior. We analyze this influence in terms of how often an attack pattern occurs and how strongly the examples carrying it jointly affect the model. This analysis motivates six corpus-level features that examine cross-modal neighborhoods, recurring text, and changes after text-span erasure without training the victim model. We introduce TraceGuard, an adaptive rank-based filtering method that uses agreement among complementary feature rankings to identify suspicious examples. It refines the selected set through shared patterns and adapts the removal threshold to each corpus without knowing the attack or poison rate. Across 19 attack configurations spanning image-text learning, generative vision-language model fine-tuning, and encoder-transfer tests, TraceGuard removes an average of 98.4% of poisoned examples and 5.4% of clean examples. After training on the filtered corpora, the residual attack metric is at most 1% in 13 configurations. Matched-removal controls and ablations support the contributions of sample selection and adaptive removal. Stress tests also identify detection failures under adaptive attacks and unnecessary removal on poison-free corpora.

cs.CR↗

arXiv2026

FedSubMuon: Communication-Efficient Federated LLM Fine-Tuning via Structured Subspace Muon

Federated fine-tuning adapts large language models (LLMs) to decentralized client data, but its scalability in cross-device training is often limited by the high communication cost. Muon is an optimizer that improves optimization performance by orthogonalizing momentum for matrix-valued parameters. Existing federated Muon methods demonstrate the benefit of matrix-aware optimization in federated learning, but still require transmitting full layer-size updates and optimizer state. A natural way to reduce communication is to directly apply Muon to LoRA factors, but this changes the optimized object and weakens Muon's matrix-aware update geometry. We propose FedSubMuon, a communication-efficient federated Muon fine-tuning method that optimizes compact coefficient matrices within shared structured subspaces. This design keeps Muon on a single matrix-valued trainable object, while reducing the client upload to compact coefficient matrices. We further introduce FedSubMuon-GT, an accuracy-oriented extension that uses projected gradients to adapt tracked subspace bases toward task-relevant gradient directions. Experiments on instruction tuning and mathematical reasoning show that FedSubMuon-GT achieves the best overall accuracy on four of five dataset-model pairs, while FedSubMuon performs best under all matched communication budgets. On Dolly-15K, the closest communication baseline requires 5.5 times and 1.4 times more total communication on Llama-1B and Qwen-4B, respectively.

cs.LG↗

arXiv2026

Inferring Hidden User Models from the Behavior of Personalized LLM Agents

Recent personalized LLM agents increasingly transform information retained in memory into compressed or structured representations, which we call user models, to guide later decisions. When source wording is removed from the state reachable through the ordinary interface, these models are commonly treated as more privacy-preserving because direct memory-extraction attacks lose the text they target. Yet we argue that user models expose a new attack surface because an attacker can still recover the private information from the personalized choices they shape, even when source records and backend state remain inaccessible. We therefore introduce UMPeek, a black-box attack based on hypothesis-guided adaptive probing to infer such hidden user model. It forms hypotheses from choices left open by a request, switches among ordinary follow-up tasks, and retains only claims supported and not contradicted by visible behavior. We conduct an extensive benchmark evaluation across diverse personalization tasks and user-model backends against existing attacks. We further validate UMPeek in real-world systems using information confirmed to be retained, and we evaluate defenses against its adaptive probing. Overall, UMPeek outperforms existing attacks in both benchmark and real-world comparisons and continues to recover user information under response-level defenses, showing that keeping records and backend state inaccessible does not guarantee semantic privacy when retained information shapes visible behavior.

cs.CR↗

arXiv2026

SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning

Visual reinforcement learning has achieved remarkable progress in visual control and robotics, but its vulnerability to adversarial perturbations remains underexplored. Most existing black-box attacks focus on vector-based or discrete-action RL, and their effectiveness on image-based continuous control is limited by the large action space and excessive environment queries. We propose SEBA, a sample-efficient framework for black-box adversarial attacks on visual RL agents. SEBA integrates a shadow Q model that estimates cumulative rewards under adversarial conditions, a generative adversarial network that produces visually imperceptible perturbations, and a world model that simulates environment dynamics to reduce real-world queries. Through a two-stage iterative training procedure that alternates between learning the shadow model and refining the generator, SEBA achieves strong attack performance while maintaining efficiency. Experiments on MuJoCo and Atari benchmarks show that SEBA significantly reduces cumulative rewards, preserves visual fidelity, and greatly decreases environment interactions compared to prior black-box and white-box methods. The code is available at https://github.com/tairanhuang/seba online.

cs.LG↗

arXiv2026

CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?

Prompt injection attacks on Large Language Model (LLM) agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underlying LLMs to execute harmful actions outside their benign scope. While current defenses effectively counter known injection attacks, deploying them in LLM agent environments remains challenging due to attack variants and emerging threats. Moreover, existing solutions typically suffer from an inherent trilemma, i.e., a constant trade-off among runtime efficiency, contextual precision, and adaptability. To bridge this gap, we propose Continuous Agents for Injection Threats via Lifelong Yielding Nexus (CAITLYN), an agent-agnostic defense middleware. CAITLYN integrates two systems. System I focuses on immediate defense against existing attacks using a two-tiered library: Tier-0 for rule-based detection scripts and Tier-1 for optimized LLM-based accurate inference. System II, in contrast, is deployed to monitor potential abnormal signals and attempt to synthesize new defenses. On standard benchmarks, CAITLYN matches the detection performance of state-of-the-art defenses at lower token overhead than LLM-as-a-judge baselines. On Emerging, our new delivery-aware benchmark featuring novel injection techniques, static baselines and the standalone System I configuration remain vulnerable. In contrast, System II autonomously synthesizes verified defense capabilities, substantially lowering the attack success rate across three diverse agent environments.

cs.CR↗

arXiv2026

IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off

Personalized text-to-image diffusion models (e.g., DreamBooth, LoRA) enable users to synthesize high-fidelity avatars from a few reference photos for social expression. However, once these generations are shared on social media platforms (e.g., Instagram, Facebook), they can be linked to the real user via face recognition systems, enabling identity tracking and profiling. Existing defenses mainly follow an anti-personalization strategy that protects publicly released reference photos by disrupting model fine-tuning. While effective against unauthorized personalization, they do not address another practical setting in which personalization is authorized, but the resulting public outputs still leak identity information. To address this problem, we introduce a new defense setting, termed model-side output immunization, whose goal is to produce a personalized model that supports authorized personalization while reducing the identity linkability of public generations, with tunable control over the privacy-utility trade-off to accommodate diverse privacy needs. To this end, we propose Identity-Decoupled personalized Diffusion Models (IDDM), a model-side defense that integrates identity decoupling into the personalization pipeline. Concretely, IDDM follows an alternating procedure that interleaves short personalization updates with identity-decoupled data optimization, using a two-stage schedule to balance identity linkability suppression and generation utility. Extensive experiments across multiple datasets, diverse prompts, and state-of-the-art face recognition systems show that IDDM consistently reduces identity linkability while preserving high-quality personalized generation.

cs.CV↗

arXiv2026

How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework

Overestimation in evaluating large language models (LLMs) has become an increasing concern. Due to the contamination of public benchmarks or imbalanced model training, LLMs may achieve unreal evaluation results on public benchmarks, either intentionally or unintentionally, which leads to unfair comparisons among LLMs and undermines their realistic capability assessments. Existing benchmarks attempt to address these issues by keeping test cases permanently secret, mitigating contamination through human evaluation, or repeatedly collecting and constructing new samples. However, these approaches fail to ensure reproducibility, transparency, and high efficiency simultaneously. Moreover, the extent of overestimation in current LLMs remains unquantified. To address these issues, we propose ArxivRoll, a dynamic evaluation framework inspired by one-time pad encryption in cryptography. ArxivRoll comprises two key components: \emph{i) SCP (Sequencing, Cloze, and Prediction)}, an automated generator for private test cases, and \emph{ii) Rugged Scores (RS)}, metrics that measure the proportion of public benchmark contamination and training bias. Leveraging SCP, ArxivRoll constructs a new benchmark every six months using recent articles from ArXiv and employs them for one-time evaluations of LLM performance. Extensive experiments demonstrate the high quality of our benchmark, and we provide a systematic evaluation of current LLMs. The source code is available at https://github.com/liangzid/ArxivRoll/.

cs.CL↗

arXiv2026

Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models

Large vision-language models (LVLMs) have achieved impressive performance across multimodal tasks, but their reliance on visual inputs exposes them to adversarial threats. Encoder-based attacks provide an efficient alternative to end-to-end optimization by crafting perturbations through the vision encoder alone. However, existing encoder-based attacks often assume that the surrogate encoder is identical or similar to the victim LVLM's vision encoder. In this work, we present a systematic study of their transferability in more realistic black-box deployments with heterogeneous LVLM architectures. We find that model-specific visual evidence is inconsistent across models, whereas text-conditioned grounding regions are more closely tied to caption-relevant evidence and provide a more stable transfer target. However, existing attacks remain weakly aligned with and insufficiently disrupt these regions. Motivated by these findings, we propose Grounding-Driven Attack (GDA), which aligns perturbation optimization with text-grounded evidence. GDA combines Grounding-Aware Perturbation Allocation to concentrate perturbation budget on grounded evidence regions with Grounding-Centric Evidence Disruption to intensify their global and local disruption. Experiments across diverse victim models and tasks show that GDA consistently outperforms existing encoder-based attacks in black-box transfer. These results highlight the central role of text-grounded evidence in adversarial transferability and motivate grounding-aware robustness evaluation and defense design.

cs.CR↗

arXiv2026

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary

Decision boundary, the subspace of inputs where a machine learning model assigns equal classification probabilities to two classes, is pivotal in revealing core model properties and interpreting behaviors. While analyzing the decision boundary of large language models (LLMs) has attracted increasing attention recently, constructing it for mainstream LLMs remains computationally infeasible due to the enormous sequence-level output spaces and the autoregressive nature of LLMs. To address this issue, in this paper we propose Decision Potential Surface (DPS), a new notion for analyzing the properties of LLM decisions. DPS is derived from the confidence in distinguishing different classes for each input, which naturally captures the potential of the decision boundary. We prove that the zero-height isohypse in DPS is equivalent to the decision boundary of an LLM, with enclosed regions representing decision regions. By leveraging DPS, for the first time in the literature, we propose a practical decision boundary approximation algorithm, namely K-DPS, which only requires only K finite sequence samples to approximate an LLM's decision boundary with negligible error. We theoretically derive the upper bounds for the absolute error, expected error, and the error concentration between K-DPS and the ideal DPS, demonstrating that such errors can be traded off against sampling times.

cs.LG↗

arXiv2026

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully disclose the robustness vulnerabilities of compressed LVLMs, due to an optimization-inference mismatch: perturbations are optimized on the full-token representation, while inference is performed through a token-compression bottleneck. To address this gap, we propose the Compression-AliGnEd attack (CAGE), which aligns perturbation optimization with compression inference without assuming access to the deployed compression mechanism or its token budget. CAGE combines (i) expected feature disruption, which concentrates distortion on tokens likely to survive across plausible budgets, and (ii) rank distortion alignment, which actively aligns token distortions with rank scores to promote the retention of highly distorted evidence. Across diverse representative plug-and-play compression mechanisms and datasets, our results show that CAGE consistently achieves lower robust accuracy than the baseline. This work highlights that robustness assessments ignoring compression can be overly optimistic, calling for compression-aware security evaluation and defenses for efficient LVLMs.

cs.CR↗