Search arXiv⌕ Search

arXiv subjects

Wei Yang Bryan Lim

Publications and source records attributed to Wei Yang Bryan Lim.

At least 19 recordsLinked to original sources
arXiv2026

VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents

Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous agents, whose semantic states are dynamically refined through a recurrent process known as collaborative reflection. While this mechanism improves recommendation quality, it simultaneously introduces a systemic vulnerability: adversarial evidence injected into a single agent can be rationalised into a legitimate preference narrative, written back into memory, and propagated to other agents through interaction contexts. We term the local rationalisation process reflection laundering, and its system-wide escalation through collaborative reflection collaborative-reflection hijacking. Existing attacks on recommender systems, whether based on interaction-level data poisoning or text-level adversarial perturbations, assume static pipelines and thus cannot exploit this recurrent, multi-agent amplification pathway. To bridge this gap, we first conduct a controlled vulnerability analysis that establishes two exploitable properties underlying collaborative-reflection hijacking: reflective persistence and cross-agent propagation. Then building on these findings, we propose VirusCascade, the first black-box targeted promotion attack that jointly shapes semantic and structural attack surfaces: the former ensures the target item is naturally rationalised as satisfying broad user preferences, the latter positions it for system-wide propagation. Extensive experiments on four real-world datasets across diverse LLM-ARS architectures demonstrate that VirusCascade consistently achieves state-of-the-art targeted exposure under evaluated stealth constraints, reaching a mean E@20 of 0.384 and surpassing the strongest baseline by an absolute margin of +0.185.

cs.CR↗
arXiv2026

FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence

Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to real-world claims, creating new challenges for verifying visual evidence. A concrete emerging risk is AI-generated refund fraud, in which manipulated or synthetic images are used to support claims about damaged products, poor delivery conditions, or service-related defects. Existing AI-generated image detection benchmarks mainly evaluate standalone authenticity classification, cross-generator transfer, or forensic localization, leaving claim-conditioned fraudulent evidence detection underexplored. To bridge this gap, we introduce FraudBench, a multimodal benchmark for detecting AI-generated fraudulent refund evidence. FraudBench is constructed from real-world user-review evidence across e-commerce, food delivery, and travel-service scenarios. We curate real evidence images together with their associated review and product metadata, identify genuine damaged and undamaged evidence through MLLM-assisted filtering and human annotation, and synthesize fake-damaged evidence from genuine undamaged reference images using 12 state-of-the-art image editing and generation models. Using FraudBench, we evaluate MLLMs, specialized AI-generated image detectors, and human evaluators on the same evaluation images. Experiments show that current MLLMs often recognize real-damaged evidence but fail on many fake-damaged subsets, with fake-damage detection rates (TPR) far below the 50\% baseline on most generator subsets. Specialized detectors generally perform better but remain inconsistent across generators and can produce false positives on real-damaged samples, revealing a clear gap between generic AI image detection and reliable claim-conditioned refund-evidence verification.

cs.CV↗
arXiv2026

Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recurring routines. Existing approaches retrieve task-relevant history and append it to the policy's context, implicitly assuming that experience relevant to a task remains useful for each decision within it. We find that this help is largely spent at the first decision: retrieved history strongly improves the opening step of an episode, yet provides little sustained benefit over the remaining 90\% of steps, and offers weak guidance on whether a proactive suggestion is warranted. A relevant record may tell the agent where to begin, but not which past action applies to the current screen or whether a routine is due now. The underlying issue is that relevance does not imply applicability}: relevance is determined at the task level, whereas applicability depends on the situation at decision time. We therefore recast personalization as experience activation and introduce ExpActivator, a training-free framework that activates only the experience applicable to the current situation. During execution, ExpActivator matches each new screen to historical states in the frozen GUI backbone's latent space and supplies the corresponding action as a reference. Before execution, it activates a recurring intent only when the current time and scenario provide sufficient support, and otherwise abstains. Across four GUI backbones, ExpActivator improves within-trajectory step success by 28\% on average, achieves the best personalized execution on every backbone while using about one-fifth as many history tokens, and reaches approximately 2.3$\times$ the Matthews correlation coefficient of the strongest proactive baseline. Experience pays where it is activated, not where it is appended.

cs.CV↗
arXiv2026

Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure

Concept erasure aims to suppress undesirable knowledge in text-to-image generative models. However, existing robustness evaluations typically rely on relearning attacks tailored to specific model architectures. We study concept reactivation across two substantially different generative paradigms: noise-prediction U-Nets and flow-matching Transformers. We introduce \textbf{Concept Score Relearning (CSR)}, a unified parameter-level framework that reactivates erased concepts by optimizing each model within its native prediction space. CSR requires no external target-concept image dataset and applies the same concept-directed objective to both U-Net-based Stable Diffusion and Transformer-based FLUX. Experiments across diverse concepts and multiple erasure methods demonstrate consistent concept reactivation across both architectures, highlighting the cross-architecture applicability of CSR and the persistent recoverability of apparently erased concepts. For strict nudity, CSR reaches average ASRs of 50.47\% on FLUX and 40.29\% on Stable Diffusion, consistently ranking first across all evaluated safety settings.

cs.CV↗
arXiv2026

CoCurve: Cross-Module Co-Pruning Curvature for Structured LLM Pruning

Resource-constrained deployment requires sustaining large language model (LLM) capabilities as models scale under fixed memory and computation budgets. Structured pruning advances this deployment frontier with smaller dense checkpoints, yet deciding what to prune remains bottlenecked by interactions among joint removals. We introduce Cross-Module Co-Pruning Curvature (CoCurve), which formulates structured pruning as set-dependent predictive risk over a unified inventory of attention heads and feed-forward groups. A co-pruning graph built from single-unit forward ablations assigns individual risk to nodes and reinforcement or cancellation to interaction edges, conditioning each decision on the units already removed. We evaluate 6 LLMs (3B--70B) and 3 vision--language models (VLMs) across 3 perplexity corpora, 12 language tasks, and 7 multimodal benchmarks. Across the five-model 20--40% grid and the 70B 10--50% sweep, CoCurve ranks first in 53/60 corpus comparisons (15/15 at 70B); matched-quality interpolation permits 2.2--6.6 more pruning points in 9/10 cases, while CoCurve leads all 6 VLM Avg$_7$ blocks. After the same lightweight recovery, its retained structures remain strongest through 50% pruning, where the 8B checkpoint regains 10.8 Avg$_{12}$ points; physical slicing delivers $1.58\times$ dense prefill throughput with 41% lower peak memory. Mechanism analysis across 10 LLMs and 7 VLMs finds organized within- and cross-module edge structure; matched low-saliency, high-coupling removals degrade 19/20 capability groups by up to 23.7 points.

cs.LG↗
arXiv2026

State of Thought Enables Endogenous Reasoning

Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasoning paradigms rely heavily on externally imposed control, either through fixed reasoning programs or through costly expansion in constrained search spaces, limiting both generalization and efficiency. We propose State of Thought (SoT), a new reasoning paradigm that enables endogenous reasoning in LLMs, with the model's internal reasoning state governing how reasoning unfolds. Concretely, SoT extracts a compact dynamics-geometric state from the model's internal information transfer and uses a 582-parameter controller on frozen backbones to selectively activate historical reasoning support useful under the current reasoning state, framing reasoning as a state-conditioned process over evidence rather than an externally prescribed token chain. Across quantitative (1.34x), general (1.62x), symbolic-and-code (1.76x), and long-context (2.51x) reasoning on 3 LLMs and 16 datasets, SoT consistently improves mean-baseline accuracy while reducing generated tokens by 62.6% and end-to-end latency by 44.6%. Across 2 VLM scales and 3 reasoning tasks, it improves mean accuracy by 3.8 points over reasoning baselines, with 74.9% fewer completion tokens and 73.5% lower latency than search-based methods. Under constrained access, SoT retains 38.2%/36.5% mean accuracy gains in training-free/embedding-only settings, while trajectory-only judging reaches 84.1% agreement across 3 API models. Together, endogenous state-driven reasoning provides a generalizable and efficient alternative.

cs.CL↗
arXiv2026

Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

Mechanistic interpretability seeks to explain transformer behavior through circuits: sets of internal components that causally support a behavior. However, self-repair creates a blind spot: ablating a primary component can activate a dormant backup, so a circuit that explains behavior in the intact model can become incomplete under the intervention used to test it. We formulate this gap as conditional circuit completion: given a primary set, identify components that become causally important after its removal. We introduce conditional co-ablation (CoAx), which ranks candidates by growth in ablation effect after primary-set removal. We show that a perfectly dormant backup can be indistinguishable from an irrelevant component to per-unit intact-state scores, whereas its conditional effect change exactly aggregates all interaction orders linking it to the removed set. On GPT-2-small's Indirect Object Identification (IOI) circuit, CoAx recovers the documented backup heads at 0.941 ROC-AUC, versus 0.815 for the strongest intact-state attribution baseline and 0.758 for the matched conditional-energy control. Recovery drops to 0.40 +/- 0.13 AUC for alternative component sets matched in behavioral effect, output displacement, and depth, showing that recovery is specific to the removed circuit. Beyond recovery, the CoAx-selected heads are causally load-bearing: freezing them after primary removal sharply reduces the IOI margin, while adding them to the incomplete circuit reduces incompleteness from 0.75 to 0.21. More broadly, conditional growth aligns with intervention-derived repair in 11/12 held-out instances across 4 mechanism clusters, and CoAx completions outperform matched random completions on all 8 non-GPT-2 models spanning 6 architecture families. Together, causal explanations of self-repairing transformers must account for backup circuitry when primary components fail.

cs.LG↗
arXiv2026

Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions

Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these effects in Jev, a non-generative decision model, using 510 reconstructed InjecAgent cases. Malicious content shifts action probabilities but rarely causes Jev to select the attacker's target. Override markers reduce this influence, while claims of contextual relatedness have small effects. Adaptive attacks using score feedback double the mean highest attacker-target probability found during optimization, while success on fresh validation calls rises from 1.8% to 3.5%. Exploratory analysis links these successes to small initial decision margins or greater attacker control over the observation. Together, these findings show that schema-defined outputs change but do not eliminate prompt-injection risk, highlighting the need to evaluate how untrusted content influences choices within the allowed action set.

cs.CR↗
arXiv2026

REFLEX with Jev for Efficient Selective Control in LLM Agents

LLM agents often use generative models for bounded decisions, raising the question of when these decisions can be handled more efficiently without reducing task success. We study REFLEX, an agent architecture that uses Jev as a fast, typed decision layer and calls a strong LLM when confidence is low, or generation is required. On a frozen 100-task benchmark, REFLEX achieves 95% success with 72.7% fewer strong-model calls than a strong-only agent, with reductions persisting across three fallback families. Controlled interventions show that reliability depends on action-set size and near-valid alternatives near authorization boundaries. External BFCL and $τ$-style evaluations reveal limited advantages over a cheap generative cascade when ordinary routing is already highly accurate. These findings identify when selective control with Jev can reduce computation and where its benefits are limited.

cs.AI↗
arXiv2026

Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning

One-shot federated graph learning (FGL) requires the server to estimate client contributions from highly compressed information, yet conventional volume-based weighting captures the amount of client data while overlooking how its connectivity is organized. In this paper, we propose SPIRE, a Structural Entropy-Driven Graph Diffusion Generation method that introduces topology-aware client differentiation into one-shot FGL. Specifically, we employ first-order degree-distribution structural entropy as a compact descriptor of degree-mass dispersion and use it to derive structural client weights, providing an inductive bias that accounts for differences in graph topology beyond data volume. On the generation side, a graph diffusion model on the server synthesizes pseudographs conditioned on the weighted client prototypes, capturing both semantic and structural information without requiring additional client-side training. The generated pseudographs are then assembled via disjoint union fusion to train a global graph neural network. Extensive experiments on seven real-world graph datasets demonstrate that SPIRE consistently outperforms conventional and one-shot FGL methods, with particularly strong gains under highly heterogeneous (non-IID) and graph-perturbed settings.

cs.LG↗
arXiv2026

Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models

Large language models (LLMs) are increasingly involved in group decision-making with other LLMs and humans. Yet it remains unclear whether their influence is driven by persuasion-oriented expression or compliance-oriented accommodation. We introduce DecisionQE, a questionnaire-based framework for measuring each model's persuasive and compliant tendencies across multiple decision scenarios, and use the Werewolf game as an interactive testbed to study their effects on social influence and group outcomes under asymmetric information. Across experiments, stronger persuasive tendency does not significantly improve group outcomes, whereas compliant-oriented models show more stable advantages in cooperation. We further reveal a dual effect of compliance: it supports cooperation in honest roles but improves concealment in adversarial roles. These findings suggest that LLM group interactions reveal not only task outcomes, but also measurable patterns of intrinsic behavioral tendency. LLMs can therefore serve as a lens for sociological observation of language-mediated interaction, while highlighting the need to incorporate behavioral tendencies into safety evaluation of LLM systems.

cs.AI↗
arXiv2026

SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains

Computer-use agents~(CUAs) have transformed large language models into persistent execution systems capable of generating, storing, and reusing artifacts like skills and memory entries. However, existing security defenses largely treat attacks as externally triggered or temporally bounded, leaving a critical gap in addressing how compromise can propagate internally through an agent's own persistent state. We reveal that malicious influence can be covertly embedded into the structural redundancies of autonomously synthesized artifacts, allowing it to survive internal state updates and bypass standard vetting mechanisms. To formalize this threat, we introduce SynChain, a self-synthesized attack paradigm utilizing persistence-aware directed supervised fine-tuning to induce agents to create poisoned yet benign-looking artifacts. To systematically evaluate this propagation, we construct CUAChain, a dataset comprising 30 benign task chains and three attack objectives. SynChain enables dormant payloads to seamlessly reactivate in future workflows as trusted context, operating entirely without new malicious exogenous inputs. Extensive experiments on OpenClaw, Codex, and Claude Code under four defense settings demonstrate that SynChain achieves high attack success and outperforms adapted baselines, proving that securing CUAs requires provenance-aware reasoning over cross-task execution trajectories.

cs.CR↗
arXiv2026

Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle

Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technical interventions must be applied earlier, when content is released or accessed. This survey examines the protective paradigm that has grown around this intervention point, which we call \emph{adversarial attacks for good}. Perturbations and structured signals long studied as attacks on learned models are instead applied by data owners, creators, platforms, or auditors to disrupt unauthorized automation or support later accountability. Five research communities have arrived at this inversion largely independently, each addressing a different stage of a visual asset's lifecycle: privacy filters against unwanted recognition at sharing time, unlearnable examples against unauthorized training, generative safeguards against malicious editing or imitation, adversarial CAPTCHAs for access control against automated agents, and provenance mechanisms for post-circulation attribution. Although developed in separate venues with incompatible success criteria, many of these methods exploit persistent gaps between human perception, semantic interpretation, and machine inference, suggesting that the paradigm remains relevant as visual pipelines evolve toward multimodal models and autonomous agents. To make their claims comparable, we evaluate all five families along shared axes of transferability, adaptability, and deployment readiness. Across the lifecycle, we find that most protections are still validated mainly against static or weakly adaptive adversaries, while evidence beyond controlled benchmarks remains scarce. We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.

cs.CR↗
arXiv2026

VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems

Multimodal large language models (MLLMs) are pushing recommender systems (RecSys) toward content-grounded retrieval and ranking via cross-modal fusion. We find that while cross-modal consensus often mitigates conventional poisoning that manipulates interaction logs or perturbs a single modality, it also introduces a new attack surface where synchronised multimodal poisoning can reliably steer fused representations along stable semantic directions during fine-tuning. To characterise this threat, we formalise cross-modal interactive poisoning and propose VENOMREC, which performs Exposure Alignment to identify high-exposure regions in the joint embedding space and Cross-modal Interactive Perturbation to craft attention-guided coupled token--patch edits. Experiments on four real-world multimodal datasets demonstrate that VENOMREC consistently outperforms strong baselines, achieving 0.73 mean ER@20 and improving over the strongest baseline by +0.52 absolute ER points on average, while maintaining comparable recommendation utility. Code is available at https://github.com/GuoweiGuan666/VenomRec.

cs.CR↗
arXiv2026

MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models

Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individuals through hierarchical chain-of-thought reasoning. However, existing privacy benchmarks remain structurally insufficient for this threat, as they primarily evaluate privacy perception while failing to address the more critical risk of privacy reasoning: a VLM's ability to infer and link distributed information to construct individual profiles. To address this gap, we propose MultiPriv, the first benchmark designed to systematically evaluate individual-level privacy reasoning in VLMs. We introduce the Privacy Perception and Reasoning (PPR) framework and construct a bilingual multimodal dataset with synthetic individual profiles, where identifiers, such as faces and names, are linked to sensitive attributes. This design enables nine challenging tasks spanning attribute detection, cross-image re-identification, and chained inference. We conduct a large-scale evaluation of over 50 open-source and commercial VLMs. In our controlled benchmark, 60% of widely used VLMs can perform individual-level privacy reasoning with up to 80% accuracy, suggesting a significant potential threat to personal privacy. The benchmark is available at https://github.com/CyberChangAn/MultiPriv-PII.

cs.CV↗
arXiv2026

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Representation Engineering analyses often characterize refusal using static directions extracted from terminal or pooled representations. We ask whether this view misses how refusal is constructed across layer-token positions. Using causal tracing, we identify a \textit{Refusal Trajectory}: a sparse upstream activation pattern that often persists even when attacks such as GCG suppress terminal refusal signals. Based on this observation, we propose SALO (Sparse Activation Localization Operator), a lightweight white-box detector that operates on raw hidden-state volumes from a selected layer window. Across Qwen, Llama, and Mistral models, SALO improves jailbreak detection on several attack families under a fixed XSTest-calibrated operating point. We further analyze static RepE-style baselines, ROI sensitivity, adaptive GCG attacks, and encoded-input boundary cases, clarifying both the promise and limitations of refusal-trajectory monitoring.

cs.CR↗
arXiv2026

MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose MPU, an algorithm-agnostic privacy-preserving Multiple Perturbed Copies Unlearning framework that primarily introduces two server-side modules: Pre-Process for randomized copy generation and Post-Process for update aggregation. In Pre-Process, the server distributes multiple perturbed and reparameterized model instances, allowing the client to execute unlearning locally on its private forget set without accessing the server's exact original parameters. After local unlearning, the server performs Post-Process by inverting the reparameterization and aggregating updates with a harmonic denoising procedure to alleviate the impact of perturbation. Experiments with seven unlearning algorithms show that MPU achieves comparable unlearning performance to noise-free baselines, with most algorithms' average degradation well below 1% up to 10% noise, and can even outperform the noise-free baseline for some algorithms under 1% noise. Code is available at https://github.com/Tristan0318/MPU.

cs.LG↗
arXiv2026

XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition

Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characterized. Existing benchmarks primarily focus on single-turn restricted scenarios, failing to capture the capability boundaries exposed by real-world interactive scientific workflows. To address this, we introduce XDomainBench, a diagnostic benchmark for interactive interdisciplinary scientific reasoning. We formalize the composition order and mixture structure to enable systematic stress-testing from single-discipline to inter-disciplinary, comprising 8,598 interactive sessions across 20 domains and 4 task categories, with 8 realistic trajectory patterns covering difficulty and domain-mixture dynamics, simulating real AI4S scenarios. Large-scale evaluation of LLMs reveals a systematic reasoning collapse as composition order increases, stemming from two root causes: (i) direct difficulty increases induced by domain composition, and (ii) indirect interaction-amplified failures where trajectory patterns trigger error accumulation, reasoning breaks, and domain confusion, ultimately leading to session collapse.

cs.AI↗