arXiv subjects

Chih-Hong Cheng

Publications and source records attributed to Chih-Hong Cheng.

At least 19 recordsLinked to original sources

arXiv2026

Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration

Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recovers held-out forget-set ROUGE for every method we evaluate, and we trace this fragility to optimization geometry. The per-token answer margin of fourteen post-hoc methods spanning gradient, preference, and distillation families converges into a narrow band above the retain reference in 41 of 42 method--size cells, a regularity we call the margin cliff. We prove that this cliff follows whenever the retain coupling holds the diagnostic log-odds of forget content above a floor, a condition that token-saturating losses induce at stationarity and that we verify directly on 34 of 42 cells. Margin Calibration (\textsc{MC}) is a plug-in polish adding a non-saturating margin hinge anchored at the reference's per-token margin plus a KL probe on a disjoint instruction corpus, restoring forget-side pressure where the native loss saturates. Under a stated gradient-dominance condition, whose on-trajectory gradient signature we measure by instrumenting the polish, its stationary set lies on the cliff-crossing side, yielding an attack-budget upper bound on the relearn margin lift. Across TOFU (three Llama-3 sizes, three forget tiers), MUSE-News on Llama-2-7B-hf, and a Phi-3.5 panel, a single frozen configuration wins all 14 head-to-head forget aggregates and all populated relearn cells (panel-mean post-attack ROUGE-L $0.41$ to $0.18$) and lowers raw membership AUC on 13/14, with reduced retain-side utility as the main cost. A deployment variant matches these gains without a retain-trained reference.

cs.AI↗

arXiv2026

A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models

Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder layer. We compare five defence candidates across 15 model and layer cells from four architectural families under a magnitude controlled protocol that matches the intervention size for each prompt and pairs every direction with a random control of the same norm. The candidates are the mean image conditioning shift, a CMRM style refusal direction, a ShiftDC style attack specific residual, a prompt instruction to ignore the image, and a random control. No single candidate dominates on both refusal recovery and utility preservation. The image conditioning shift leads on LLaVA 1.5 and Pixtral 12B and is the only candidate whose utility loss remains at the measurement noise floor in every family. The prompt instruction leads on Qwen2.5 VL, while the attack specific residual leads on Qwen2 VL 2B. The image conditioning direction is direction specific in 13 of 15 cells, but strongly architecture specific and nontransferable across the only dimension compatible pair, LLaVA 1.5 13B and Pixtral 12B. We also connect text only and multimodal refusal geometry. The CMRM direction has positive cosine alignment with the image conditioning shift in all 15 cells, with mean 0.35, range 0.17 to 0.65, 15 to 25 times the random vector null, and a sign test p value of about 3e-5. These results show that the two recipes recover partially overlapping geometry and that direction based defences should be calibrated separately for each language decoder family.

cs.AI↗

arXiv2026

Safety-Aligned 3D Object Detection: Single-Vehicle, Cooperative, and End-to-End Perspectives

Perception plays a central role in connected and autonomous vehicles (CAVs), underpinning not only conventional modular driving stacks, but also cooperative perception systems and recent end-to-end driving models. While deep learning has greatly improved perception performance, its statistical nature makes perfect predictions difficult to attain. Meanwhile, standard training objectives and evaluation benchmarks treat all perception errors equally, even though only a subset is safety-critical. In this paper, we investigate safety-aligned evaluation and optimization for 3D object detection that explicitly characterize high-impact errors. Building on our previously proposed safety-oriented metric, NDS-USC, and safety-aware loss function, EC-IoU, we make three contributions. First, we present an expanded study of single-vehicle 3D object detection models across diverse neural network architectures and sensing modalities, showing that gains under standard metrics such as mAP and NDS may not translate to safety-oriented criteria represented by NDS-USC. With EC-IoU, we reaffirm the benefit of safety-aware fine-tuning for improving safety-critical detection performance. Second, we conduct an ego-centric, safety-oriented evaluation of AV-infrastructure cooperative object detection models, underscoring its superiority over vehicle-only models and demonstrating a safety impact analysis that illustrates the potential contribution of cooperative models to "Vision Zero." Third, we integrate EC-IoU into SparseDrive and show that safety-aware perception hardening can reduce collision rate by nearly 30% and improve system-level safety directly in an end-to-end perception-to-planning framework. Overall, our results indicate that safety-aligned perception evaluation and optimization offer a practical path toward enhancing CAV safety across single-vehicle, cooperative, and end-to-end autonomy settings.

cs.CV↗

arXiv2026

ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces corpus poisoning as a new attack surface. In this setting, an adversary injects or edits passages so that they enter the Top-$K$ results for target queries and influence downstream generation. Existing defences often rely on content filtering, auxiliary models, or generator-side reasoning, which complicates deployment. We propose ProGRank, a post hoc, training-free retriever-side defence for dense-retriever RAG. ProGRank stress-tests each query--passage pair under mild randomized perturbations, extracts probe gradients from a small fixed parameter subset, and derives two instability signals: representational consistency and dispersion risk. It then combines these signals with a score gate for reranking. ProGRank preserves the original passage content, requires no retraining, and supports a surrogate-based variant when the deployed retriever is unavailable. Experiments across datasets, retrievers, attacks, and retrieval-stage and end-to-end settings show that ProGRank improves robustness and maintains a favorable robustness--utility trade-off, including under adaptive evasive attacks.

cs.AI↗

arXiv2026

Workflow-Level Design Principles for Trustworthy GenAI in Automotive System Engineering

The adoption of large language models in safety-critical system engineering is constrained by trustworthiness, traceability, and alignment with established verification practices. We propose workflow-level design principles for trustworthy GenAI integration and demonstrate them in an end-to-end automotive pipeline, from requirement delta identification to SysML v2 architecture update and re-testing. First, we show that monolithic ("big-bang") prompting misses critical changes in large specifications, while section-wise decomposition with diversity sampling and lightweight NLP sanity checks improves completeness and correctness. Then, we propagate requirement deltas into SysML v2 models and validate updates via compilation and static analysis. Additionally, we ensure traceable regression testing by generating test cases through explicit mappings from specification variables to architectural ports and states, providing practical safeguards for GenAI used in safety-critical automotive engineering.

cs.SE↗

arXiv2026

Validating Generalist Robots with Situation Calculus and STL Falsification

Generalist robots are becoming a reality, capable of interpreting natural language instructions and executing diverse operations. However, their validation remains challenging because each task induces its own operational context and correctness specification, exceeding the assumptions of traditional validation methods. We propose a two-layer validation framework that combines abstract reasoning with concrete system falsification. At the abstract layer, situation calculus models the world and derives weakest preconditions, enabling constraint-aware combinatorial testing to systematically generate diverse, semantically valid world-task configurations with controllable coverage strength. At the concrete layer, these configurations are instantiated for simulation-based falsification with STL monitoring. Experiments on tabletop manipulation tasks show that our framework effectively uncovers failure cases in the NVIDIA GR00T controller, demonstrating its promise for validating general-purpose robot autonomy.

cs.RO↗

arXiv2025

Quantifying Fidelity: A Decisive Feature Approach to Comparing Synthetic and Real Imagery

Virtual testing using synthetic data has become a cornerstone of autonomous vehicle (AV) safety assurance. Despite progress in improving visual realism through advanced simulators and generative AI, recent studies reveal that pixel-level fidelity alone does not ensure reliable transfer from simulation to the real world. What truly matters is whether the system-under-test (SUT) bases its decisions on consistent decision evidence in both real and simulated environments, not just whether images "look real" to humans. To this end this paper proposes a behavior-grounded fidelity measure by introducing Decisive Feature Fidelity (DFF), a new SUT-specific metric that extends the existing fidelity spectrum to capture mechanism parity, that is, agreement in the model-specific decisive evidence that drives the SUT's decisions across domains. DFF leverages explainable-AI methods to identify and compare the decisive features driving the SUT's outputs for matched real-synthetic pairs. We further propose estimators based on counterfactual explanations, along with a DFF-guided calibration scheme to enhance simulator fidelity. Experiments on 2126 matched KITTI-VirtualKITTI2 pairs demonstrate that DFF reveals discrepancies overlooked by conventional output-value fidelity. Furthermore, results show that DFF-guided calibration improves decisive-feature and input-level fidelity without sacrificing output value fidelity across diverse SUTs.

cs.AI↗

arXiv2025

Randomized Smoothing Meets Vision-Language Models

Randomized smoothing (RS) is one of the prominent techniques to ensure the correctness of machine learning models, where point-wise robustness certificates can be derived analytically. While RS is well understood for classification, its application to generative models is unclear, since their outputs are sequences rather than labels. We resolve this by connecting generative outputs to an oracle classification task and showing that RS can still be enabled: the final response can be classified as a discrete action (e.g., service-robot commands in VLAs), as harmful vs. harmless (content moderation or toxicity detection in VLMs), or even applying oracles to cluster answers into semantically equivalent ones. Provided that the error rate for the oracle classifier comparison is bounded, we develop the theory that associates the number of samples with the corresponding robustness radius. We further derive improved scaling laws analytically relating the certified radius and accuracy to the number of samples, showing that the earlier result of 2 to 3 orders of magnitude fewer samples sufficing with minimal loss remains valid even under weaker assumptions. Together, these advances make robustness certification both well-defined and computationally feasible for state-of-the-art VLMs, as validated against recent jailbreak-style adversarial attacks.

cs.LG↗

arXiv2025

Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deployment

Evaluating object detection models in deployment is challenging because ground-truth annotations are rarely available. We introduce the Cumulative Consensus Score (CCS), a label-free monitoring signal for continuous evaluation and comparison of detectors in real-world settings. CCS applies test-time data augmentation to each image and measures the spatial consistency of predicted bounding boxes across augmented views using Intersection over Union. The resulting consensus score serves as a proxy for reliability without requiring bounding box annotations. In controlled experiments on Open Images and KITTI, CCS achieved over 90% congruence with F1-score, Probabilistic Detection Quality, and Optimal Correction Cost, with qualitative consistency further confirmed on COCO and BDD100K across model pairs. The method is model-agnostic, working across single-stage and two-stage detectors, and operates at the case level to highlight under-performing scenarios. We also provide a simplified theoretical link between expected CCS and detection correctness. Altogether, CCS provides a robust foundation for DevOps-style monitoring of object detectors.

cs.CV↗

arXiv2025

LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers

Fine-tuning large language models (LLMs) improves performance on domain-specific tasks but can lead to overfitting, making them unreliable on out-of-distribution (OoD) queries. We propose LoRA-BAM - a method that adds OoD detection monitors to the LoRA layer using boxed abstraction to filter questions beyond the model's competence. Feature vectors from the fine-tuning data are extracted via the LLM and clustered. Clusters are enclosed in boxes; a question is flagged as OoD if its feature vector falls outside all boxes. To improve interpretability and robustness, we introduce a regularization loss during fine-tuning that encourages paraphrased questions to stay close in the feature space, and the enlargement of the decision boundary is based on the feature variance within a cluster. Our method complements existing defenses by providing lightweight and interpretable OoD detection.

cs.LG↗

arXiv2025

Rethinking Code Review Workflows with LLM Assistance: An Empirical Study

Code reviews are a critical yet time-consuming aspect of modern software development, increasingly challenged by growing system complexity and the demand for faster delivery. This paper presents a study conducted at WirelessCar Sweden AB, combining an exploratory field study of current code review practices with a field experiment involving two variations of an LLM-assisted code review tool. The field study identifies key challenges in traditional code reviews, including frequent context switching, insufficient contextual information, and highlights both opportunities (e.g., automatic summarization of complex pull requests) and concerns (e.g., false positives and trust issues) in using LLMs. In the field experiment, we developed two prototype variations: one offering LLM-generated reviews upfront and the other enabling on-demand interaction. Both utilize a semantic search pipeline based on retrieval-augmented generation to assemble relevant contextual information for the review, thereby tackling the uncovered challenges. Developers evaluated both variations in real-world settings: AI-led reviews are overall more preferred, while still being conditional on the reviewers' familiarity with the code base, as well as on the severity of the pull request.

cs.SE↗

arXiv2025

On the Need for a Statistical Foundation in Scenario-Based Testing of Autonomous Vehicles

Scenario-based testing has emerged as a common method for autonomous vehicles (AVs) safety assessment, offering a more efficient alternative to mile-based testing by focusing on high-risk scenarios. However, fundamental questions persist regarding its stopping rules, residual risk estimation, debug effectiveness, and the impact of simulation fidelity on safety claims. This paper argues that a rigorous statistical foundation is essential to address these challenges and enable rigorous safety assurance. By drawing parallels between AV testing and established software testing methods, we identify shared research gaps and reusable solutions. We propose proof-of-concept models to quantify the probability of failure per scenario (\textit{pfs}) and evaluate testing effectiveness under varying conditions. Our analysis reveals that neither scenario-based nor mile-based testing universally outperforms the other. Furthermore, we give an example of formal reasoning about alignment of synthetic and real-world testing outcomes, a first step towards supporting statistically defensible simulation-based safety claims.

cs.SE↗

arXiv2025

Revisiting Out-of-Distribution Detection in Real-time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigm

Out-of-distribution (OoD) inputs pose a persistent challenge to deep learning models, often triggering overconfident predictions on non-target objects. While prior work has primarily focused on refining scoring functions and adjusting test-time thresholds, such algorithmic improvements offer only incremental gains. We argue that a rethinking of the entire development lifecycle is needed to mitigate these risks effectively. This work addresses two overlooked dimensions of OoD detection in object detection. First, we reveal fundamental flaws in widely used evaluation benchmarks: contrary to their design intent, up to 13% of objects in the OoD test sets actually belong to in-distribution classes, and vice versa. These quality issues severely distort the reported performance of existing methods and contribute to their high false positive rates. Second, we introduce a novel training-time mitigation paradigm that operates independently of external OoD detectors. Instead of relying solely on post-hoc scoring, we fine-tune the detector using a carefully synthesized OoD dataset that semantically resembles in-distribution objects. This process shapes a defensive decision boundary by suppressing objectness on OoD objects, leading to a 91% reduction in hallucination error of a YOLO model on BDD-100K. Our methodology generalizes across detection paradigms such as YOLO, Faster R-CNN, and RT-DETR, and supports few-shot adaptation. Together, these contributions offer a principled and effective way to reduce OoD-induced hallucination in object detectors. Code and data are available at: https://gricad-gitlab.univ-grenoble-alpes.fr/dnn-safety/m-hood.

cs.CV↗

arXiv2024

FuzzRisk: Online Collision Risk Estimation for Autonomous Vehicles based on Depth-Aware Object Detection via Fuzzy Inference

This paper presents a novel monitoring framework that infers the level of collision risk for autonomous vehicles (AVs) based on their object detection performance. The framework takes two sets of predictions from different algorithms and associates their inconsistencies with the collision risk via fuzzy inference. The first set of predictions is obtained by retrieving safety-critical 2.5D objects from a depth map, and the second set comes from the ordinary AV's 3D object detector. We experimentally validate that, based on Intersection-over-Union (IoU) and a depth discrepancy measure, the inconsistencies between the two sets of predictions strongly correlate to the error of the 3D object detector against ground truths. This correlation allows us to construct a fuzzy inference system and map the inconsistency measures to an AV collision risk indicator. In particular, we optimize the fuzzy inference system towards an existing offline metric that matches AV collision rates well. Lastly, we validate our monitor's capability to produce relevant risk estimates with the large-scale nuScenes dataset and demonstrate that it can safeguard an AV in closed-loop simulations.

cs.RO↗

arXiv2024

Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey

Text-to-Image (T2I) Diffusion Models (DMs) have garnered widespread attention for their impressive advancements in image generation. However, their growing popularity has raised ethical and social concerns related to key non-functional properties of trustworthiness, such as robustness, fairness, security, privacy, factuality, and explainability, similar to those in traditional deep learning (DL) tasks. Conventional approaches for studying trustworthiness in DL tasks often fall short due to the unique characteristics of T2I DMs, e.g., the multi-modal nature. Given the challenge, recent efforts have been made to develop new methods for investigating trustworthiness in T2I DMs via various means, including falsification, enhancement, verification \& validation and assessment. However, there is a notable lack of in-depth analysis concerning those non-functional properties and means. In this survey, we provide a timely and focused review of the literature on trustworthy T2I DMs, covering a concise-structured taxonomy from the perspectives of property, means, benchmarks and applications. Our review begins with an introduction to essential preliminaries of T2I DMs, and then we summarise key definitions/metrics specific to T2I tasks and analyses the means proposed in recent literature based on these definitions/metrics. Additionally, we review benchmarks and domain applications of T2I DMs. Finally, we highlight the gaps in current research, discuss the limitations of existing methods, and propose future research directions to advance the development of trustworthy T2I DMs. Furthermore, we keep up-to-date updates in this field to track the latest developments and maintain our GitHub repository at: https://github.com/wellzline/Trustworthy_T2I_DMs

cs.LG↗

arXiv2024

Estimating the Robustness Radius for Randomized Smoothing with 100$\times$ Sample Efficiency

Randomized smoothing (RS) has successfully been used to improve the robustness of predictions for deep neural networks (DNNs) by adding random noise to create multiple variations of an input, followed by deciding the consensus. To understand if an RS-enabled DNN is effective in the sampled input domains, it is mandatory to sample data points within the operational design domain, acquire the point-wise certificate regarding robustness radius, and compare it with pre-defined acceptance criteria. Consequently, ensuring that a point-wise robustness certificate for any given data point is obtained relatively cost-effectively is crucial. This work demonstrates that reducing the number of samples by one or two orders of magnitude can still enable the computation of a slightly smaller robustness radius (commonly ~20% radius reduction) with the same confidence. We provide the mathematical foundation for explaining the phenomenon while experimentally showing promising results on the standard CIFAR-10 and ImageNet datasets.

cs.LG↗

arXiv2024

Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIs

The deployment of generative AI (GenAI) models raises significant fairness concerns, addressed in this paper through novel characterization and enforcement techniques specific to GenAI. Unlike standard AI performing specific tasks, GenAI's broad functionality requires ``conditional fairness'' tailored to the context being generated, such as demographic fairness in generating images of poor people versus successful business leaders. We define two fairness levels: the first evaluates fairness in generated outputs, independent of prompts and models; the second assesses inherent fairness with neutral prompts. Given the complexity of GenAI and challenges in fairness specifications, we focus on bounding the worst case, considering a GenAI system unfair if the distance between appearances of a specific group exceeds preset thresholds. We also explore combinatorial testing for assessing relative completeness in intersectional fairness. By bounding the worst case, we develop a prompt injection scheme within an agent-based framework to enforce conditional fairness with minimal intervention, validated on state-of-the-art GenAI systems.

cs.LG↗

arXiv2024

BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection

Out-of-distribution (OoD) detection techniques for deep neural networks (DNNs) become crucial thanks to their filtering of abnormal inputs, especially when DNNs are used in safety-critical applications and interact with an open and dynamic environment. Nevertheless, integrating OoD detection into state-of-the-art (SOTA) object detection DNNs poses significant challenges, partly due to the complexity introduced by the SOTA OoD construction methods, which require the modification of DNN architecture and the introduction of complex loss functions. This paper proposes a simple, yet surprisingly effective, method that requires neither retraining nor architectural change in object detection DNN, called Box Abstraction-based Monitors (BAM). The novelty of BAM stems from using a finite union of convex box abstractions to capture the learned features of objects for in-distribution (ID) data, and an important observation that features from OoD data are more likely to fall outside of these boxes. The union of convex regions within the feature space allows the formation of non-convex and interpretable decision boundaries, overcoming the limitations of VOS-like detectors without sacrificing real-time performance. Experiments integrating BAM into Faster R-CNN-based object detection DNNs demonstrate a considerably improved performance against SOTA OoD detection techniques.

cs.CV↗