Preprocessing-based defenses are the standard first-line response to adversarial attacks on edge vision systems, requiring no retraining, no architectural changes, and widely recommended as model-agnostic mitigations. Yet the foundational evaluations of these defenses were conducted on residual or Inception-class architectures, not on the depthwise-separable CNNs that dominate edge deployments. This untested assumption leaves a gap in the security evaluation literature. This paper closes that gap by evaluating six preprocessing defenses against adversarial perturbations across both architecture families. Across all perturbation levels and defenses tested, the two depthwise-separable architectures show consistently poor recovery while the residual architecture shows partial recovery; ablation results are consistent with an architectural rather than parametric explanation, though only three architectures and one attack family are evaluated. Crucially, this failure is not merely a negative result. The same output divergence that disqualifies preprocessing as a recovery mechanism reveals a detection opportunity: preprocessing consistently disrupts clean predictions while leaving adversarial predictions largely unchanged, an asymmetry that is directly measurable without retraining or architectural modification. We further show that standard image quality metrics are unreliable proxies for defense effectiveness, a methodological gap in current evaluation practice. A practitioner decision framework is provided for adversarially resilient edge vision deployment.
Despite recent advances in large vision-language models (LVLMs), object hallucination remains a major barrier to their reliable deployment. Existing detection methods often characterize visual grounding using attention from individual layers, leaving its evolution across layers underexplored. We propose CADMP, a lightweight object hallucination detection framework that combines adjacent-layer cross-modal attention drift with prediction sensitivity to targeted visual masking. During decoding, CADMP quantifies distributional changes between consecutive cross-modal attention maps to capture abrupt transitions in visual grounding. It then selects the transition with the largest drift, locates the corresponding visually relevant regions, and measures the change in prediction probability after masking these regions. These two signals provide complementary evidence: attention drift characterizes the stability of internal visual grounding, while probability variation verifies whether a prediction truly depends on the identified visual evidence. A lightweight detector integrates both signals to identify hallucinated predictions. Experiments on multiple benchmarks and representative open-source LVLMs demonstrate that CADMP achieves consistently competitive detection performance. Ablation studies further confirm the complementary contributions of adjacent-layer drift modeling and mask-based grounding verification.
We propose BlobBoards, a fiducial marker system comprising a dense, multi-scale field of Gaussian blobs and a feature-based pipeline for joint detection, identification, and pose estimation. Each board is registered from hundreds of blob features whose dense spatial coverage constrains pose, while multiple scales preserve detectability across large changes in focal length, distance, and obliquity. Learned local descriptors are matched to the reference pattern and spatially verified, so the correspondences determine pose and certify identity. Against motion-capture ground truth, BlobBoards achieve median translation errors of 3.6-5.0 mm, reducing AprilTag's median translation error by 89% on small boards and 70% on large ones. They also produce far fewer large-rotation failures than state-of-the-art tag systems. BlobBoards achieve the highest detection rate, 80% versus 74% for AprilTag and 58% for ArUco, with the largest margin on the smallest markers. Under 50% occlusion, they still detect 69% of boards with essentially unchanged median translation error, while AprilTag and ArUco detect none. In experiments BlobBoards give state-of-the-art detection rate, pose accuracy and occlusion robustness.
When a code generating language model fabricates a Python package name, an adversary who has pre-registered that name on PyPI can convert that hallucination into a supply chain compromise. This event has been termed as 'slopsquatting'. We propose a two layer detector to counter this issue. The first layer performs a deterministic PyPI existence check. The second is a Random Forest classifier trained on ten features derived from the package name and its PyPI metadata. An import name reconciler bridges the two, resolving cases such as 'import cv2' versus 'pip install opencv-python' without a security bypass. The detector is embedded in a LangGraph state machine that retries at escalating temperatures and, on repeated failure, routes to a stronger fallback model. Across 300 curated prompts, the pipeline produces hallucination free code on 76% of runs. The primary exhausts its retry budget on 28.7%; intra model retries recover roughly a quarter of those, and cross model fallback recovers a further 16.5% of the remainder. Four findings have been observed. First, half of the flagged hallucinations are packages already registered on PyPI, as low quality lookalikes of well known projects, caught by the classifier rather than the deterministic layer (e.g., pil, faiss, tabula, haystack). Second, hallucination rate scales almost linearly with prompt adversariality, from 0 to 10% on routine coding to 40 to 73% on slopsquat baits. Third, the weaker primary refused 6 of 10 direct baits unaided, suggesting recent instruction tuning provides a baseline defense. Fourth, when primary and fallback share a model family, approximately 84% of primary failures recur on the fallback, motivating cross family pairing. A user study (n = 24) reports mean satisfaction 4.4 out of 5 and 21 of 24 stated adoption intent.
Sycophantic responses are becoming pervasive in large language models (LLMs), and prior work has pointed out that some of them could be harmful. This paper focuses on one harmful sycophancy: preference-induced stance reversal sycophancy (PSRS), where a model reverses an initial stance merely to align with a user's stated preference. While existing research mainly measures how sycophantic a model is, we go further and ask whether PSRS can also be detected automatically from a single response. To investigate this at scale, we introduce CAP (Contrastive Anchor Probing), a framework for collecting labeled PSRS data. Applying CAP to 17 open- and closed-source LLMs, we collect 290,460 labeled responses across 12 everyday-advice domains. We organize our study around three research questions. (1) How often does PSRS occur? (2) How well can it be detected? (3) How does detection generalize to unseen models? We first reveal that PSRS rates range from 5% to 56% across LLMs, with more capable models being less sycophantic. Next, we show that detecting PSRS is feasible from the response text alone, and detectors need to learn subtle PSRS patterns from the training data. Because new LLMs appear rapidly, detectors inevitably encounter unseen models, making cross-model generalization an important framework goal. We demonstrate that detection performance drops on unseen models and propose an initial approach to address this challenge. We will release our dataset and code to support future research.
Accurate estimation of left ventricular (LV) orientation is essential for cardiac magnetic resonance (CMR) imaging and downstream analysis. Existing methods typically formulate orientation recognition as discrete view classification or rely on multi-slice geometric intersection, limiting their ability to model continuous 3D orientation and generalize across arbitrary slices. This work introduces a novel paradigm: Joint LV localization and 3D orientation estimation from a single CMR slice. To investigate this setting, representative orientation-aware detection frameworks are adapted to the CMR domain, and their limitations are analyzed. Upon that, we propose the Polar-Coupled Circular (PCC) embedding that provides a continuous and unambiguous orientation representation to address the limitations. Meanwhile, a scalable benchmark is constructed through automatic slice sampling from volumetric CMR segmentation datasets. Extensive experiments on four datasets demonstrate strong performance, achieving an average mIoU of 86.18% and an average angle deviation of 3.39°. This study establishes a new task setting for single-slice LV orientation modeling and provides a geometry-consistent framework for spatially informed CMR analysis. Code is available at https://github.com/yuyi1005/cmr-3d-ood.
Traffic forecasting by graph-based AI is a critical component of intelligent transportation systems, motivating security research on robustness to malicious sensor readings. We argue that prior robustness evaluations are largely shaped by unrealistic threat models and untargeted objectives, so both attacks and defenses must be revisited. We study a practical adversary with limited model knowledge and the ability to monitor and manipulate only a few road sensors. More importantly, practical attacks can be localized to specific links or routes, causing incorrect estimated arrival times or unnecessary rerouting while leaving the broader network largely unaffected. This targeted setting remains underexplored, and defenses such as adversarial training do not transfer well from the norm-bounded attacks they train on to structurally different, physics-aware attacks that mimic genuine congestion. We therefore reframe robustness as a detection problem, introducing a learned physics-informed detector whose output is fed to a hardened forecaster as an input feature and trained against adaptive attacks with the forecaster fixed. We evaluate across a variety of model architectures and benchmarks. The physics-aware attack multiplies target-link error several-fold while the network-wide error barely moves, and adversarial training, tuned to norm-bounded perturbations, barely dents it. Our detection--mitigation defense improves even on adversarial training hardened against the physics-aware attack itself, on $13$ of $15$ model--dataset settings and by the widest margin on a held-out attack, at near-zero clean cost. The results emphasize the need to examine abstracted AI adversarial attacks under application-specific constraints to assess their true security impacts.
Computer vision models are increasingly used as measurement tools to estimate population-level quantities from large image collections, but prediction errors introduce bias and the resulting estimates lack statistical guarantees required in scientific applications. Prior work uses a Monte Carlo framework to combine model predictions with ground-truth annotations by sampling some images for humans to label and is able to provide unbiased estimates with controllable accuracy, but primarily addresses single-scalar estimation. We study the more general problem of multi-target estimation, where many quantities (e.g., class counts or proportions) must be estimated simultaneously, and adapt sampling and estimation strategies from survey sampling to this setting. Evaluations on five detection and segmentation datasets with 7-80 classes show that importance sampling excels with moderate annotation budgets or fewer targets, whereas uniform sampling with control variates is superior when estimating many targets or operating with minimal labels. Additionally, a subset-based ratio estimator remains highly competitive across all regimes. Ultimately, our framework effectively combines biased model predictions and limited human labels into rigorous scientific measurements.
The lifecycle of hallucination in LLMs is a concept that enables building solid frameworks on the control and reliability of LLMs in high-stakes environments, including health, legal, and scientific research. Although previous surveys have primarily focused on detection or mitigation, this survey provides a lifecycle-based overview of the hallucinations in the LLMs, their cause, detection, mitigation, and prevention.We propose a three-fold categorization of hallucinations across the LLM lifecycle: data-related, training-related, and inference-related, which is consistent with the lifecycle of the development of the LLM. Each of these stages is discussed regarding the cause of hallucinations, their detection, and the ways they can be addressed under specific mitigation or prevention interventions. In addition, we discuss the available benchmark data using a number of parameters so as to establish their suitability in identifying, restricting and managing hallucinations. The survey provides researchers and practitioners with a standardized framework to understand, diagnose, and cure hallucinations in a systematic system to present actionable data to build safer and more reliable LLMs.
With the development of generative AI, watermarking techniques have been widely used to detect the authenticity of AI-generated data and protect the rights of users and creators. While it is already well applied in data types including imaging and text data, watermarking tabular data is still under-explored. Existing methods primarily focus on numerical data, leaving discrete, categorical, and mixed data less studied. In this work, we propose STAMP (Single-observation Tabular Attribution and Marking Procedure), a novel framework for watermarking tabular data that can accommodate and preserve a wide range of distributions. We also develop a corresponding detection mechanism, which can reliably identify watermarks even when the sample size is as small as one. We establish theoretical guarantees for asymptotic consistency and detection accuracy. Finally, through extensive simulation studies and two real-data applications, we demonstrate that the proposed method is effective and robust to subsetting, while maintaining data fidelity and a high detection rate.
Bihe Zhao, Louis Kerner, Michel Meintz +3cs.CV cs.AI
Image autoregressive models (IARs) have recently demonstrated remarkable capabilities in visual content generation, achieving photorealistic quality and rapid synthesis through the next-token prediction paradigm adapted from large language models. As these models become widely accessible, robust data provenance is required to reliably trace IAR-generated images to the source model that synthesized them. This is critical to prevent the spread of misinformation, detect fraud, and attribute harmful content. We find that although IAR-generated images often appear visually identical to real images, their generation process introduces characteristic patterns in their outputs, which serves as a reliable provenance signal for the generated images. Leveraging this, we present a post-hoc framework that enables the robust detection of such patterns for provenance tracing. Notably, our framework does not require modifications of the generative process or outputs. Thereby, it is applicable in contexts where prior watermarking methods cannot be used, such as for generated content that is already published without additional marks and for models that do not integrate watermarking. We demonstrate the effectiveness of our approach across a wide range of IARs, highlighting its high potential for robust data provenance tracing in autoregressive image generation.
Understanding hands and the objects they interact with, both directly and through tools, is a key step for tasks ranging from action perception to 3D reconstruction and robotics. Our paper provides several contributions to the Hand-Object Interaction (HOI) understanding literature: (1) HOI-DETR, a new framework that introduces hand-object and object-object interactions to the Co-DETR architecture to produce a state-of-the-art method; (2) a comprehensive HOI evaluation suite of 4 diverse datasets, including a video benchmark derived from the HD-EPIC dataset and fresh annotations that improve the Hands23 benchmark and (3) a trained checkpoint that significantly improves the state of the art across Hands23, HOIST, FineBio, and HD-EPIC, including mAP gains of over 20 percentage points on Hands23 and FineBio. Our ablations confirm the contributions of each model component.
Data leakage -- contamination of a model with information unavailable at baseline -- is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise. None operates on the artifact an auditor most often holds: the model's output. We ask what can be decided about leakage from predictions and outcomes alone. We give a decision-theoretic framework in which leakage diagnostics are functionals of the predicted-risk/outcome law, parameterized by a threshold-weighting linked to proper scoring rules and decision-curve analysis. We prove a sharp impossibility: a recalibrated leak matching an honest model's calibration and discrimination is indistinguishable from honest performance by \emph{any} function of the predictions, so the broad class is detectable only against an externally supplied ceiling on achievable discrimination. We then prove what leakage cannot hide: a near-deterministic subgroup -- the signature of a near-label leak -- produces a sustained unit-purity head that no legitimate predictor of a non-deterministic outcome can manufacture, yielding a prior-free test. These results organize leakage into a trichotomy -- miscalibrated, broad-calibrated, and deterministic -- each with a matched detector and failure mode. We validate on UK Biobank using time-windowed comorbidity leakage with known, graded severity, measuring a detection floor of $Δ\cstar \approx 0.007$ on this endpoint, below which residual leakage is undetectable from output and too small to alter conclusions. The numerical floor is cohort- and endpoint-specific; the structural lesson is general: output-only detection fails where residual leakage is indistinguishable from an honestly stronger predictor. The test returns a verdict on a prediction vector in under a second on commodity hardware.
Watermarking methods for language models have been studied extensively in the autoregressive setting, where tokens are generated sequentially. These works largely focus on local-context schemes that perturb the next token's distribution as a function of its preceding tokens. In diffusion language models, distributions over many unresolved positions are jointly sampled, allowing additive statistics of the entire sequence to be tractable during generation. We propose a watermark for masked diffusion language models that controls a global, vector-valued sketch representation of the text. Compared to context-dependent watermarking, the sketch formulation decouples detection from the local contexts seen during generation, resulting in an order-agnostic statistic and a watermarking rule which does not manifest as a simple token bias. We analyze the distortion, soundness, and robustness properties of the method.
While diffusion models excel at generating high-quality images, their tendency to memorize training data poses significant privacy and copyright risks. In this work, we for the first time identify that memorization induces internal numerical instability, often manifesting as visually ``broken'' artifacts. Inspired by stability analysis in numerical methods, we introduce empirical stability regions based on latent update norms to quantitatively characterize stable behavior during generation. Leveraging this, we propose a principled, on-the-fly framework for step-wise detection and adaptive mitigation. Our approach suppresses memorization without altering prompts or guidance, thereby preserving semantic fidelity and image quality. Extensive experiments on Stable Diffusion 1.4 demonstrate that our method achieves an AUC $>0.999$ detection performance and a $0.0\%$ memorization rate after mitigation with negligible overhead ($\approx0.01$s per image).
Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature in the model's residual stream: each phase shift moves the activation, producing a total path length far exceeding benign conversations. We call this adversarial restlessness. Five scalar trajectory features capturing this signal lift conversation-level detection from 76.2% to 93.8% on synthetic held-out data. The signal replicates across four model families (24B-70B); probes are model-specific and do not transfer across architectures. Generalization is source-dependent: leave-one-source-out evaluation shows each of synthetic, LMSYS-Chat-1M, and SafeDialBench captures distinct attack distributions, with detection on real-world LMSYS reaching 47-71% when its distribution is represented in training. Combined three-source training achieves 89.4% detection at 2.4% false positive rate on a held-out mixed set. We further show that three-phase turn-level labels(benign/pivoting/adversarial) unique to our synthetic dataset are essential: binary conversation-level labels produce 50-59% false positives. These results establish adversarial restlessness as a reliable activation-level signal and characterize the data requirements for practical deployment.