Searcharxiv⌕ Search

arXiv subjects

Ee-Chien Chang

Publications and source records attributed to Ee-Chien Chang.

At least 19 recordsLinked to original sources
arXiv2026

Provably Secure Diffusion Watermarking Against Removal Adversaries with Batched Detector Access

Recent latent-based watermarking methods can embed undetectable watermarks into AI-generated content. However, these approaches are vulnerable to removal attacks as their watermark detection boundaries are exposed, prompting the use of secret long-term transformations to hide these boundaries. We show that such defenses are insecure under a stronger threat model motivated by publicly reachable detectors: an adversary with batched detector access can reconstruct the transformations, permanently re-exposing the decision boundary. To address this, we propose a watermarking scheme based on a hybrid of long-term and one-time secret transformations, which prevents the reuse of structure across samples and keeps the long-term secret hidden. Besides undetectability, we show that this scheme is provably secure against removal adversaries with batched detector access, in the sense that no probabilistic polynomial-time adversary can achieve a non-negligible advantage over an adversary restricted to adding isotropic white-noise with a $\sqrt{2}\times$ larger perturbation budget, and we show this $\sqrt{2}$ factor to be tight. Evaluations on Stable Diffusion 2.1 and XL demonstrate the attack against the existing defense, and show that our scheme preserves generation quality and withstands common perturbations and targeted removal attacks.

cs.CR↗
arXiv2026

ClockMark: Adaptive and Host-Dependent Watermarking for Large Language Models

Large language model (LLM) watermarking operates on the next-token distribution that evolves during generation. In streaming generation, each sampled token becomes part of the text and affects subsequent distributions. Embedding therefore proceeds with a changing host, unlike classical watermarking, which adapts embedding to an existing host signal. To accommodate this difference, we formulate a novel embedding framework for LLM watermarking based on two principles. We first argue that embedding should be adaptive, retaining the state of previous sampling decisions to better guide subsequent choices. We further argue that embedding should be host-dependent, using the current LLM distribution to constrain both token selection and state updates. Guided by these principles and the two requirements of distribution preservation and robustness to text editing, we propose ClockMark. It combines adaptive and host-dependent embedding with message spreading, embedding the full payload in each watermarked token. Theoretically, we prove that ClockMark preserves the original LLM sequence distribution, thereby maintaining generation quality. Empirically, extensive experiments against 12 baselines demonstrate improved robustness to text editing, with gains of up to 16.08 percentage points in bit accuracy over the strongest tested baseline.

cs.LG↗
arXiv2026

Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models

Low-Rank Adaptation (LoRA) has made diffusion model personalization affordable and widely shareable, but it also creates moderation risks when harmful or problematic content is not faithfully disclosed. Hence, it is desired to develop a mechanism that, given a LoRA adapter, discovers the concept it was trained to generate, so as to support downstream investigation. We characterize the target concept through the conditioning input that most clearly exposes what the LoRA has learned. Such an input should induce coherent LoRA outputs that are distinctive from those of the base model and strongly align with the learned LoRA subspace. We therefore formulate concept discovery as searching for the conditioning input that jointly maximizes output coherence, LoRA-induced distinctiveness, and subspace alignment. Even with a clear objective, however, optimizing it over an open-ended input space is prohibitively expensive, since reliable evaluation of coherence and distinctiveness requires repeated diffusion rendering. Crucially, we observe that an input need not be rendered to determine whether it is promising. Its alignment with the learned LoRA subspace provides a lightweight signal for localizing promising candidates before visual verification. Based on this insight, we develop a two-stage framework for text-to-image LoRAs. Subspace-Guided Evolutionary Search (SGES) uses render-free subspace alignment to explore candidate prompts and retain a compact shortlist, while Paired Visual Identification (PVI) renders only these candidates and compares the LoRA and base-model outputs to identify those exhibiting coherent and distinctive generation behavior. This design enables efficient and reliable discovery of previously unknown concepts encoded in LoRA adapters.

cs.AI↗
arXiv2026

Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains

Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm, bringing the long-overlooked issue of confidence faithfulness to the forefront. A promising solution jointly optimizes unsupervised Reinforcement Learning from Internal Feedback (RLIF) with reasoning-trace-guided Reasoning Distillation (RD), yet it faces three persistent challenges, namely the scarcity of high-quality training corpora, factually unwarranted overconfidence, and erroneous updates amplified by indiscriminate fusion. Inspired by how human confidence accumulates from uncertainty to certainty, we propose Progressive Reasoning Gain (PRG) to measure whether reasoning steps progressively strengthen confidence in the final answer. Building on PRG, we introduce HyTuning, a hybrid post-training framework that adaptively reweights RD and RLIF, using scarce supervised reasoning traces as a stable anchor while exploiting abundant unlabeled queries for scalability. Experiments on several domain-specific and general benchmarks demonstrate that HyTuning improves accuracy while achieving confidence faithfulness under limited supervision, supporting a practical ``Less Data Approximates More'' effect. Our code will be released upon acceptance.

cs.LG↗
arXiv2026

ZoneClaw: Mitigating Persistent Memory Attacks by Establishing Memory-Zoning in OpenClaw-Style Computer-Use Agents

Computer-use agents increasingly operate as long-running assistants through persistent workspace memory, which OpenClaw-style CUAs realize as automatically reloaded files that hold user instructions, system summaries, and external claims at the same privilege level. Here, remembering a claim confers authority over later behavior. This enables a persistent memory attack, in which an attacker who controls only benign-looking external content induces the CUA to record attacker-favored claims during a legitimate task, and those claims later govern benign tasks the attacker never touches. The attack chain extends "malicious context -> malicious response" into "malicious context -> memory injection -> malicious execution", making this a cross-environment threat. Existing defenses studied intervene either before content enters memory or at the action it later induces, not whether stored content may guide action. We propose ZoneClaw, which separates persistence from authority by replacing flat workspace memory with hierarchical trust zones carrying explicit authority levels. External claims persist in a low-trust zone and acquire action-guiding authority only by crossing an explicit authority boundary, at which promotion is cross-checked against zones the attacker cannot directly write. Role-specific processes of asymmetric privilege enforce this boundary, ensuring that no process both ingests external content and acts outward. Across four attack scenarios, two injection settings, and four backbones, ZoneClaw drives ASR from 372/480 to 6/480 while retaining utility in 458/480 trials, and remains effective against some defense-aware attackers. Attacker claims still persist in low-trust memory yet rarely cross the authority boundary, showing that ZoneClaw withholds authority rather than refusing to learn from the environment. Our code is available at: https://github.com/euph00/ZoneClaw-code.

cs.CR↗
arXiv2026

Proof-of-Authorship for Diffusion-based AI Generated Content

Recent advancements in AI-generated content (AIGC) have introduced new challenges in intellectual property protection and the authentication of generated objects. We focus on scenarios in which an author seeks to assert authorship of an object generated using latent diffusion models (LDMs), in the presence of adversaries who attempt to falsely claim authorship of objects they did not create. While proof-of-ownership has been studied in the context of multimedia content through techniques such as time-stamping and watermarking, these approaches face notable limitations. In contrast to traditional content creation sources (e.g., cameras), the LDM generation process offers greater control to the author. Specifically, the random seed used during generation can be deliberately chosen. By binding the seed to the author's identity using cryptographic functions, the author can assert to be the creator of the object. We refer to this stronger guarantee as proof-of-authorship, since only the creator of the object can legitimately claim the object. This contrasts with proof-of-ownership via time-stamping or watermarking, where any entity could potentially claim ownership of an object by being the first to timestamp or embed the watermark. We propose a proof-of-authorship framework involving a probabilistic adjudicator who quantifies the probability that a claim is false. Furthermore, unlike prior approaches, the proposed framework does not involve any secret. We explore various attack scenarios and analyze design choices using Stable Diffusion 2.1 and XL as representative case studies.

cs.CR↗
arXiv2026

Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent Systems

A centralized LLM-based multi-agent system (MAS) extends its functionality by registering new worker agents, whose descriptions are read by the planner to decide how a task is decomposed, which worker executes each subtask, and what each subtask requires. Third-party descriptions are authored outside the system but trusted by the planner, creating a registration-time injection channel. The payload is planted before any user instruction arrives, targets the planner and propagates through the generated plan to benign workers, taking effect even when the crafted worker is never assigned a subtask or invoked. We define four worker-description fields: functionality, input specification, output specification, and usage constraints. Among 32,000 descriptions from three public agent marketplaces, most omit input specifications and usage constraints, while at least 23.35% contain content outside these fields. We construct eight description-manipulation attack strategies targeting task decomposition, capability grounding, and subtask specification, and evaluate them on GAIA. In the most severe cases, a single manipulated description reduces task success from 84.31% to 37.25%, or increases token consumption or execution time by over 111%, while the user objective remains unchanged and workers faithfully execute the resulting plan. These effects persist across two MAS implementations, six planner LLMs, four LLM evaluators, and the real-world descriptions from three marketplaces. We further propose DescGuard, a registration-time defense that retains only worker-scoped interface information before descriptions reach the planner. DescGuard restores the targeted planning metrics and downstream performance toward their baseline levels without modifying worker implementations, the planner, or the orchestration logic, and composes with existing isolation, permission-control, and runtime mechanisms.

cs.CR↗
arXiv2026

CASIAL: Geometric Distortion Robust Image Watermarking

Deep learning-based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations remains limited. Such transformations induce two fundamental failure modes: region removal, such as cropping or masking, which eliminates the information carried by removed pixels, and desynchronization, such as scaling or rotation, which misaligns pixel positions and disrupts decoding. We argue that achieving geometric robustness requires two essential properties: (1) global spread of the watermark message, ensuring resilience even when large regions are removed, and (2) geometry-invariant representations, enabling decoding to remain synchronized despite spatial transformations. Building on these insights, we propose CASIAL, a geometric distortion-robust watermarking framework with cover image-aware message spreading (CAS) strategy and invariance alignment learning (IAL) module. CAS tightly couples watermark bits with cover image features and distributes them adaptively across the entire image, enhancing per-pixel information capacity and robustness to region removal. IAL leverages spatial attention to capture cross-pixel dependencies and align perturbed features into a shared geometry-invariant representation space, mitigating failures due to desynchronization. Across six challenging geometric transformations, CASIAL achieves substantially stronger robustness than eleven prior baselines while preserving high visual quality. It also maintains competitive performance under six signal distortions and four photometric transformations. Notably, although trained only with white-box distortions, CASIAL also exhibits strong transfer robustness to unseen black-box distortions. Comprehensive experiments demonstrate the broad robustness and superior visual quality of our method.

cs.CV↗
arXiv2026

Enhancing Stateful Detection of Adversarial Attacks with Soft-labels' Temporality and Robust Similarity Approximations

Stateful Detection (SD) mitigates adversarial attacks by determining whether a sequence of queries contains queries from a black-box adversary. Recent works, such as Blacklight and PIHA utilize query similarity to detect such queries. In this paper, we observe that temporal information, in particular, the temporal correlation of the classification soft labels, is a prominent characteristic of adversarial attacks and can be leveraged to reduce false positive rates. Moreover, we point out a potential vulnerability in SD implementation. Many SD systems identify similar queries according to some implicit, computationally expensive metric. To improve efficiency, these systems often adopt an approximate similarity function as substitute. This discrepancy could be exploited by crafting queries that appear dissimilar under the approximation but are close in the intended metric, thereby evading detection. We refer to this as an ``adversarial attack'' on the approximation function, and demonstrate it through a lightweight attack on Blacklight's similarity function. Based on the above observations, we propose a two-phase approach. The first phase identifies subsequences of queries with high similarity, incorporating randomness to prevent the aforementioned ``adversarial attacks''. The second phase analyzes temporal correlation of the soft-labels to further validate the presence of the adversary's queries. Experimental results show that the framework detects adversarial queries generated by Boundary Attack, HSJA, SimBA, Square Attack with true positive rate (TPR) reaching 1.00, while maintaining a false positive rate (FPR) of at most 0.06. Additionally, the method is robust against OARS which is an adaptive attack.

cs.CR↗
arXiv2026

ResetEdit: Precise Text-guided Editing of Generated Image via Resettable Starting Latent

Recent advances in diffusion models have enabled high-quality image generation, leading to increasing demand for post-generation editing that modifies local regions while preserving global structure. Achieving such flexible and precise editing requires a high-quality starting point, a latent representation that provides both the freedom needed for diverse modifications and the precision required for fine-grained, region-specific control. However, existing inversion-based approaches such as DDIM inversion often yield unsatisfactory starting latents, resulting in degraded edit fidelity and structural inconsistency. Ideally, the most suitable editing anchor should be the original latent used during the generation process, as it inherently captures the scene's structure and semantics. Yet, storing this latent for every generated image is impractical due to massive storage and retrieval costs. To address this challenge, we propose ResetEdit, a proactive diffusion editing framework that embeds recoverable latent information directly into the generation process. By injecting the discrepancy between the clean and diffused latents into the diffusion trajectory and extracting it during inversion, ResetEdit reconstructs a resettable latent that closely approximates the true starting state. Additionally, a lightweight latent optimization module compensates for reconstruction bias caused by VAE asymmetry. Built upon Stable Diffusion, ResetEdit integrates seamlessly with existing tuning-free editing methods and consistently outperforms state-of-the-art baselines in both controllability and visual fidelity.

cs.CV↗
arXiv2026

SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents

Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended actions. This threat is further amplified for screenshot-based web agents, which operate on rendered visual webpages rather than structured textual representations, making predominant text-centric defenses ineffective. Although multimodal detection methods have been explored, they often rely on large vision-language models (VLMs), incurring significant computational overhead. The bottleneck lies in the complexity of modern webpages: VLMs must comprehend the global semantics of an entire page, resulting in substantial inference time and GPU memory usage. This raises a critical question: can we detect prompt injection attacks from screenshots in a lightweight manner? In this paper, we observe that injected webpages exhibit distinct characteristics compared to benign ones from both visual and textual perspectives. Building on this insight, we propose SnapGuard, a lightweight yet accurate method that reformulates prompt injection detection as multimodal representation analysis over webpage screenshots. SnapGuard leverages two complementary signals: a visual stability indicator that identifies abnormally smooth gradient distributions induced by malicious content, and action-oriented textual signals recovered via contrast-polarity reversal. Extensive evaluations across eight attacks and two benign settings demonstrate that SnapGuard achieves an F1 score of 0.75, outperforming GPT-4o-prompt while being 8x faster (1.81s vs. 14.50s) and introducing no additional memory overhead.

cs.CR↗
arXiv2026

ResGuard: Enhancing Robustness Against Known Original Attacks in Deep Watermarking

Deep learning-based image watermarking commonly adopts an "Encoder-Noise Layer-Decoder" (END) architecture to improve robustness against random channel distortions, yet it often overlooks intentional manipulations introduced by adversaries with additional knowledge. In this paper, we revisit this paradigm and expose a critical yet underexplored vulnerability: the Known Original Attack (KOA), where an adversary has access to multiple original-watermarked image pairs, enabling various targeted suppression strategies. We show that even a simple residual-based removal approach, namely estimating an embedding residual from known pairs and subtracting it from unseen watermarked images, can almost completely remove the watermark while preserving visual quality. This vulnerability stems from the insufficient image dependency of residuals produced by END frameworks, which makes them transferable across images. To address this, we propose ResGuard, a plug-and-play module that enhances KOA robustness by enforcing image-dependent embedding. Its core lies in a residual specificity enhancement loss, which encourages residuals to be tightly coupled with their host images and thus improves image dependency. Furthermore, an auxiliary KOA noise layer injects residual-style perturbations during training, allowing the decoder to remain reliable under stronger embedding inconsistencies. Integrated into existing frameworks, ResGuard boosts KOA robustness, improving average watermark extraction accuracy from 59.87% to 99.81%.

cs.CV↗
arXiv2026

Targeted Bit-Flip Attacks on LLM-Based Agents

Targeted bit-flip attacks (BFAs) exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models (e.g., image classifiers), LLM-based agents with multi-stage pipelines and external tools present new attack surfaces, which remain unexplored. This work introduces Flip-Agent, the first targeted BFA framework for LLM-based agents, manipulating both final outputs and tool invocations. Our experiments show that Flip-Agent significantly outperforms existing targeted BFAs on real-world agent tasks, revealing a critical vulnerability in LLM-based agent systems.

cs.CR↗
arXiv2026

AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding

Cyber Threat Intelligence (CTI) reports document observations of cyber threats, synthesizing evidence about adversaries' actions and intent into actionable knowledge that informs detection, response, and defense planning. However, the unstructured and verbose nature of CTI reports poses significant challenges for security practitioners to manually extract and analyze such sequences. Although large language models (LLMs) exhibit promise in cybersecurity tasks such as entity extraction and knowledge graph construction, their understanding and reasoning capabilities towards behavioral sequences remains underexplored. To address this, we introduce AttackSeqBench, a benchmark designed to systematically evaluate LLMs' reasoning abilities across the tactical, technical, and procedural dimensions of adversarial behaviors, while satisfying Extensibility, Reasoning Scalability, and Domain-dpecific Epistemic Expandability. We further benchmark 7 LLMs, 5 LRMs and 4 post-training strategies across 3 benchmark settings and 3 benchmark tasks within our AttackSeqBench to identify their advantages and limitations in such specific domain. Our findings contribute to a deeper understanding of LLM-driven CTI report understanding and foster its application in cybersecurity operations. Our code of benchmark construction and evaluation and the corresponding dataset are available at: https://github.com/hulkima/AttackSeqBench.

cs.CR↗
arXiv2026

TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning

Website fingerprinting (WF) attacks, which covertly monitor user communications to identify the web pages they visit, pose a serious threat to user privacy. Existing WF defenses attempt to reduce attack accuracy by disrupting traffic patterns, but attackers can retrain their models to adapt, making these defenses ineffective. Meanwhile, their high overhead limits deployability. To overcome these limitations, we introduce a novel controllable website fingerprinting defense called TrapFlow based on backdoor learning. TrapFlow exploits the tendency of neural networks to memorize subtle patterns by injecting crafted trigger sequences into targeted website traffic, causing the attacker model to build incorrect associations during training. If the attacker attempts to adapt by training on such noisy data, TrapFlow ensures that the model internalizes the trigger as a dominant feature, leading to widespread misclassification across unrelated websites. Conversely, if the attacker ignores these patterns and trains only on clean data, the trigger behaves as an adversarial patch at inference time, causing model misclassification. To achieve this dual effect, we optimize the trigger using a Fast Levenshtein like distance to maximize both its learnability and its distinctiveness from normal traffic. Experiments show that TrapFlow significantly reduces the accuracy of the RF attack from 99 percent to 6 percent with 74 percent data overhead. This compares favorably against two state of the art defenses: FRONT reduces accuracy by only 2 percent at a similar overhead, while Palette achieves 32 percent accuracy but with 48 percent more overhead. We further validate the practicality of our method in a real Tor network environment.

cs.CR↗
arXiv2026

TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking

Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit endlessly many surface forms, making jailbreak mitigation difficult. Most existing defenses depend on passive detection of suspicious suffixes, without leveraging the defender's inherent asymmetric ability to inject secrets and proactively conceal gaps. Motivated by this, we take a controllability-oriented perspective and develop a proactive defense that nudges attackers into a no-win dilemma: either they fall into defender-designed optimization traps and fail to produce an effective adversarial suffix, or they can succeed only by generating adversarial suffixes that carry distinctive, traceable fingerprints. We propose TrapSuffix, a lightweight fine-tuning approach that injects trap-aligned behaviors into the base model without changing the inference pipeline. TrapSuffix channels jailbreak attempts into these two outcomes by reshaping the model's response landscape to adversarial suffixes. Across diverse suffix-based jailbreak settings, TrapSuffix reduces the average attack success rate to below 0.01 percent and achieves an average tracing success rate of 87.9 percent, providing both strong defense and reliable traceability. It introduces no inference-time overhead and incurs negligible memory cost, requiring only 15.87 MB of additional memory on average, whereas state-of-the-art LLM-based detection defenses typically incur memory overheads at the 1e4 MB level, while composing naturally with existing filtering-based defenses for complementary protection.

cs.CR↗
arXiv2025

Removal Attack and Defense on AI-generated Content Latent-based Watermarking

Digital watermarks can be embedded into AI-generated content (AIGC) by initializing the generation process with starting points sampled from a secret distribution. When combined with pseudorandom error-correcting codes, such watermarked outputs can remain indistinguishable from unwatermarked objects, while maintaining robustness under whitenoise. In this paper, we go beyond indistinguishability and investigate security under removal attacks. We demonstrate that indistinguishability alone does not necessarily guarantee resistance to adversarial removal. Specifically, we propose a novel attack that exploits boundary information leaked by the locations of watermarked objects. This attack significantly reduces the distortion required to remove watermarks -- by up to a factor of $15 \times$ compared to a baseline whitenoise attack under certain settings. To mitigate such attacks, we introduce a defense mechanism that applies a secret transformation to hide the boundary, and prove that the secret transformation effectively rendering any attacker's perturbations equivalent to those of a naive whitenoise adversary. Our empirical evaluations, conducted on multiple versions of Stable Diffusion, validate the effectiveness of both the attack and the proposed defense, highlighting the importance of addressing boundary leakage in latent-based watermarking schemes.

cs.CR↗
arXiv2025

A Practical and Secure Byzantine Robust Aggregator

In machine learning security, one is often faced with the problem of removing outliers from a given set of high-dimensional vectors when computing their average. For example, many variants of data poisoning attacks produce gradient vectors during training that are outliers in the distribution of clean gradients, which bias the computed average used to derive the ML model. Filtering them out before averaging serves as a generic defense strategy. Byzantine robust aggregation is an algorithmic primitive which computes a robust average of vectors, in the presence of an $ε$ fraction of vectors which may have been arbitrarily and adaptively corrupted, such that the resulting bias in the final average is provably bounded. In this paper, we give the first robust aggregator that runs in quasi-linear time in the size of input vectors and provably has near-optimal bias bounds. Our algorithm also does not assume any knowledge of the distribution of clean vectors, nor does it require pre-computing any filtering thresholds from it. This makes it practical to use directly in standard neural network training procedures. We empirically confirm its expected runtime efficiency and its effectiveness in nullifying 10 different ML poisoning attacks.

cs.CR↗