We propose a fidelity-constrained framework that anchors the output of a black-box denoiser to its input without retraining and with little additional computation. The method linearly blends the denoised image with the input and selects the maximum blending factor that satisfies a prescribed local fidelity constraint using Peak Signal-to-Noise Ratio (PSNR) or Structural Similarity Index (SSIM). For PSNR control, a closed-form solution is obtained under a local constant-blending assumption. For SSIM control, we derive a tractable formulation based on inverse SSIM under the same assumption and solve it efficiently using iterative root finding. Experiments on DIV2K images with synthetic Gaussian noise and outputs from Real-ESRGAN and a non-local means denoiser show that the proposed anchoring strategy provides effective fidelity control while balancing denoising performance and statistical naturalness, as measured by the excess kurtosis of residual noise. In particular, SSIM-based anchoring yields more consistent behavior across noise levels than PSNR-based anchoring.
Typographic attacks pose a critical threat to vision-language models (VLMs) by injecting misleading text into images and causing models to rely on adversarial textual cues rather than visual evidence. Existing defenses often require model-specific modifications, additional training, or access to internal model components, limiting their applicability to modern closed-source VLMs. In this paper, we propose QuISE, a model-agnostic, training-free black-box defense based on query-irrelevant semantic editing. QuISE first identifies text regions likely to affect the current query through influence-aware text localization. QuISE then replaces these regions with two semantically distinct replacement texts that are irrelevant to both the query and the image. The final answer is determined by answer consistency across the edited images. Extensive experiments on three typographic-attack benchmarks, four attack settings, and four VLMs show that QuISE consistently improves defended accuracy. QuISE achieves a recovery rate of 67.9-75.0% with a harm rate of 0.5-1.1%.
Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment. Because deployed LLMs are commonly exposed only through query APIs, ownership verification must often rely on black-box text responses. This setting is difficult: generations are open-ended and can vary across repeated queries, while existing black-box fingerprints rely on signals that are fragile under a final-response interface, including full-text matching, soft behavioral features, or model-specific prompts designed not to transfer. We propose TCF (Targeted Counterfactual Fingerprinting), a black-box LLM fingerprinting framework that converts open-ended generation comparison into constrained-answer targeted counterfactual transfer. TCF restricts each verification query to a finite answer space, reducing the surface-form ambiguity that enters the verification score, and optimizes a prompt perturbation toward a counterfactual target different from the protected model's clean answer on the original prompt. Verification reduces to checking whether the suspect model's parsed final answer matches the recorded target. We introduce the source-model counterfactual margin (SCM), a protected-model-only quantity that certifies the target is unlikely before the perturbation and likely after it; SCM controls target selection, perturbation stopping, and fingerprint filtering. Under explicit derived-preservation and independent-transfer budgets motivated by local behavioral closeness, we derive a target-accuracy gap between derived and independent models. Across four LLM families, TCF achieves an average AUC of 0.9861, improving over TRAP, ProFLingo, and ZeroPrint by 0.07 to 0.19.
Amir Mohammad Ezzati, Kiyan Rezaee, Bardiya Kariminia +4cs.CV cs.AI
Large vision--language models (LVLMs) demonstrate strong multimodal reasoning capabilities but remain prone to hallucination, where model predictions are not grounded in visual evidence. Existing black-box hallucination detection methods estimate uncertainty through a single consistency metric, implicitly assuming that model uncertainty can be adequately characterized by a single measure. However, hallucinations exhibit diverse manifestations of uncertainty across different behavioral probes, making a single measure insufficient to characterize their underlying behavior. We propose \emph{Unique Hallucination Pattern (UHP) Detection}, a fully black-box framework that models hallucination as a structured uncertainty pattern defined by two axes: perturbation modality (image vs.\ text) and logical polarity (a statement vs.\ its negation). Their intersection produces four complementary consistency groups that capture distinct manifestations of model uncertainty, from which both within-group and between-group features are extracted to train a lightweight classifier. Through comprehensive experiments on AMBER and PhD across three LVLMs, UHP Detection consistently outperforms prior black-box and white-box baselines, with improvements of up to $+18.72\%$ AUC-ROC and $+20.07\%$ AUC-PR over the strongest black-box methods. Extensive ablation studies demonstrate that each consistency group contributes complementary information and that their combination forms a structured hallucination pattern. Furthermore, cross-dataset evaluation shows that this learned pattern generalizes across benchmarks, indicating that hallucination behavior reflects a model-specific consistency pattern. \textbf{Code is publicly available at} https://github.com/amirezzati/uhpdet.
Pirzada Suhail, Nagasai Saketh Naidu, Atanu R Sinha +1cs.CL cs.LG
Large language models (LLMs) generate text by auto-regressively sampling the next token. This inherently leads to a many-to-many mapping between prompts and responses, complicating the task of inferring prompts from observed outputs. Prior work on LLM inversion frames prompt recovery as a semantic reconstruction task. They rely on fine-tuning pretrained sequence-to-sequence models on large external datasets--and requiring access to model weights or logits--to generate semantically plausible prompts. In contrast, we present a functional approach to inverting a given LLM in a black-box setting, without auxiliary aids. We train an explicit inverse language model entirely from scratch on data synthetically generated from the target LLM itself. Analogous to forward next-token prediction, our inverse model is trained using previous-token prediction, establishing a generative link between the forward and inverse processes that enables faithful prompt reconstruction. Moreover, it naturally supports diverse prompt reconstructions through sampling, whereby all such prompts induce similar responses under the forward, target LLM. Our approach generalises across datasets and exhibits transferability in reconstructing prompts from responses generated by different LLMs. Further, across the set of token based evaluation metrics for prompt and response reconstructions, our approach outperforms prior work.
Hodaya Krakover, Meir Yossef Levi, Eyal Gofer +1cs.CV
Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or knowledge of the underlying classifier (white-box). We propose \textit{$A^4D$ (\textbf{A}ttack- and \textbf{A}rchitecture-\textbf{A}gnostic \textbf{A}dversarial \textbf{D}etector)}, a completely black-box, zero-shot adversarial attack detection framework that utilizes prompt-based similarity scores derived from CLIP. To the best of our knowledge this is the first attempt to utilize CLIP for such a task. The method is based on two key observations: (i) CLIP is sensitive even to small imperceptible non-semantic perturbations; (ii) The shift in CLIP embedding space is not arbitrary and can be used as a robust attack indicator. Experiments across multiple attacks, datasets and classifiers validate that $A^4D$ achieves SOTA detection results in the attack-agnostic and classifier-agnostic setting.
Evaluating code large language models (Code LLMs) requires reliable detection of data leakage, where benchmark performance is artificially inflated by exposure to benchmark data during pre-training. Existing approaches either assume access to proprietary training corpora, rely on brittle heuristics such as timestamp filtering, or use external reference sets with manually tuned, non-generalizable thresholds. To address these limitations, we introduce \textbf{SrDetection}, a unified \textbf{s}elf-\textbf{r}eferential leakage detection framework for both gray-box (access to model logits) and black-box (access to model outputs) settings. SrDetection generates semantically equivalent variants of a benchmark sample and detects leakage by contrasting the model's behavior on the original versus its variants, flagging cases where the original is disproportionately easier for the model. We further design a controlled leakage detection testbed and evaluate SrDetection in this environment. Across different models and training stages, SrDetection improves average F1 by 21.52 points in the gray-box setting and 14.46 points in the black-box setting over strong baselines, demonstrating robust, threshold-independent leakage detection. Finally, a gray-box study of 15 widely used Code LLMs on four popular benchmarks reveals benchmark-specific leakage patterns beyond prior overlap-based analyses\footnote{\footnotesize Source code and data are available at https://github.com/SMinL/SrDetectionCode
The rapid deployment of Vision-Language Models (VLMs) in dynamic environments necessitates the ability to learn continuously without forgetting. However, traditional continual learning (CL) settings often rely on white-box paradigms, which is increasingly invalidated by the shift toward cloud-hosted models. In this paper, we introduce Black-CL, a more realistic benchmark for VLMs that enforces three primary real-world challenges: weight and architecture inaccessibility, constrained computation, and task-agnostic inference. The learner can query only output embeddings or logits, with no gradient flow through or structural modification of the backbone. Current CL methodologies, which rely on backbone backpropagation or complex parameter expansion, are fundamentally incompatible with these constraints. Under this setting, we propose BETA, a simple yet effective baseline built on the key insight that solely optimizing textual prototypes can navigate the complexities of CL. BETA integrates three core components: Semantic Projection Accumulation (SPA) for incremental knowledge acquisition, Latent Distribution Replay (LDR) for anchoring the embedding space against catastrophic forgetting, and Test-Time Prototype Adaptation (TTPA) for dynamic, instance-aware boundary refinement. Extensive experiments across ten diverse datasets and various backbones demonstrate that BETA significantly outperforms existing black-box tuners. Remarkably, with only 0.05 M trainable parameters, a 180--3000$\times$ reduction compared to competitive methods, BETA achieves performance on par with or even exceeding white-box CL methods. We believe Black-CL and BETA provide a foundational framework for future advancements in continual learning and accelerates the transition of continual learning from academia to real-world systems.
Although large language models (LLMs) have shown strong capabilities across a wide range of tasks, their outputs often remain unreliable and may contain hallucinations, making uncertainty estimation (UE) essential for building trustworthy LLMs. In practice, many mainstream LLMs are only accessible through restricted APIs, where internal signals such as logits and hidden states are unavailable, making black-box UE especially important. However, existing work on black-box UE for LLMs remains fragmented in methodology and lacks a unified empirical comparison. To address this gap, we present a systematic review of black-box UE methods and organize them into five categories: verbalization-based, sampling-based, explanation-based, multi-agent, and hybrid methods. We further build a unified evaluation framework and benchmark 24 representative methods across 4 models and 4 dataset settings. Our results show that no single method consistently dominates across all settings. Nevertheless, methods that reason over and compare candidates in the answer space are generally effective, and hybrid methods that combine multiple uncertainty signals perform well under most conditions. By releasing the benchmark data and a unified evaluation framework, we aim to facilitate reproducible comparisons and support future research, while our empirical findings provide practical guidance for developing future black-box UE methods for LLMs.