arXiv subjects

Franziska Boenisch

Publications and source records attributed to Franziska Boenisch.

At least 19 recordsLinked to original sources

arXiv2026

AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes

Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to save deployment costs. All existing audits decide backbone identity from the text-output channel, which is structurally fragile for agentic APIs because modern serving stacks (OpenAI, Anthropic, Gemini, Cloudflare Workers AI, LangGraph) discard text and expose only structured actions when the model calls a tool, and provider-injected system prompts can distort text distributions enough that text-channel tests falsely accuse honest providers of substituting the claimed model. We observe that recent agentic post-training internalizes tool-use directly into the weights, opening a new audit channel that the serving stack still exposes and that is largely invariant to deployment context. We introduce Agentic Provenance (AgentProv), the first action-based identity audit for agentic LLM APIs: AgentProv fingerprints a deployed model through its categorical tool-call distribution and decides identity via an MMD permutation test. AgentProv catches every substituted model (100% on 630 evaluated checkpoint pairs), while holding the false-positive rate under system-prompt injection at 7% (vs. 67% for MET and 53% for RUT). On third-party API endpoints, AgentProv's disagreements with MET are consistent with an independent token-count side-channel that detects provider-injected system prompts.

cs.CR↗

arXiv2026

TabPATE: Differentially Private Tabular In-Context Learning Without Public Data

Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions. We first show that even basic membership inference attacks succeed against tabular ICL, motivating formal privacy protection. We then introduce TabPATE, a differentially private PATE-style defense for tabular ICL that does not require public in-distribution data. TabPATE partitions the private context across teacher models, privately aggregates their labels on synthetic tabular queries, and releases the resulting labeled queries as a student context. Because tabular features are bounded and relatively low-dimensional, useful queries can be generated from feature ranges alone or from lightly privatized marginals. Across tabular benchmarks, TabPATE preserves competitive utility while reducing membership inference to near-random success, providing a practical path to private tabular ICL without public data.

cs.LG↗

arXiv2026

Concept Removal for Frontier Image Generative Models

Image generative models are trained on massive, largely uncurated internet-scale datasets that contain undesirable visual concepts. Efficiently removing such concepts from the model generations without degrading the quality of output images remains challenging. We introduce a novel concept removal method for frontier diffusion and image autoregressive models, such as SD3.5, Flux, and Infinity. Our intervention replaces the internal bottleneck layer present in all these modern models with a transcoder that is trained to replicate the original layer while structuring it into distinct activation features. This in-place substitution creates an integrated filter through which concept-specific signals can be selectively disabled while preserving the rest of the model's behavior. Since the intervention modifies the model backbone rather than attaching an external component, it remains persistent under white-box access. Empirically, the approach achieves state-of-the-art concept removal performance across modern diffusion and autoregressive models, maintains visual generation quality, provides robustness against adversarial prompts, and supports sequential removal of diverse concepts. This positions our method as a practical approach for concept removal in frontier image generative models.

cs.CV↗

arXiv2026

Dataset Usage Inference without Shadow Models or Held-out Data

How much of my data was used to train a machine learning model? Dataset Usage Inference (DUI) aims to answer this by estimating what fraction of a dataset contributed to a model's training. However, existing DUI methods rely on assumptions that rarely hold in practice: they require training expensive shadow models to imitate the target model, and they assume access to both known training samples and an in-distribution held-out set confirmed to be absent from training. These conditions make current approaches impractical for modern large models and real data ownership disputes. We introduce a practical DUI framework that removes these constraints. Our method requires neither shadow models nor real held-out data. Instead, it generates synthetic non-member samples, extracts diverse membership signals, and casts DUI as a mixture proportion estimation problem to estimate what share of the candidate dataset was used during training. Experiments on large image generative models show that our method reliably quantifies dataset usage, providing a practical tool for data owners to determine how much of their data was used to train a model.

cs.LG↗

arXiv2026

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning

Memorization in machine learning models enables high performance on rare in-distribution samples by capturing their atypical patterns. However, it also causes harmful retention of noise and outliers, degrading generalization. While memorization has been extensively studied in both supervised and self-supervised learning in the vision domain, it remains unexplored in multi-modal contrastive learning. We address this gap by introducing MultiMem, the first metric designed to quantify memorization in multi-modal contrastive learning. Through our systematic analysis, we demonstrate that cross-modal semantic misalignment has the strongest influence on memorization, with text being the dominant modality driving memorization, followed by video, image, and audio. We show that targeted augmentations applied across all modalities effectively reduce memorization as measured by our MultiMem metric and improve model performance. Overall, this work establishes the first framework for measuring and mitigating memorization in multi-modal contrastive learning, preventing harmful data retention and contributing to higher-performing models.

cs.CV↗

arXiv2026

Natural Identifiers for Privacy and Data Audits in Large Language Models

Assessing the privacy of large language models (LLMs) presents significant challenges. In particular, most existing methods for auditing differential privacy require the insertion of specially crafted canary data during training, making them impractical for auditing already-trained models without costly retraining. Additionally, dataset inference, which audits whether a suspect dataset was used to train a model, is infeasible without access to a private non-member held-out dataset. Yet, such held-out datasets are often unavailable or difficult to construct for real-world cases since they have to be from the same distribution (IID) as the suspect data. These limitations severely hinder the ability to conduct scalable, post-hoc audits. To enable such audits, this work introduces natural identifiers (NIDs) as a novel solution to the above-mentioned challenges. NIDs are structured random strings, such as cryptographic hashes and shortened URLs, naturally occurring in common LLM training datasets. Their format enables the generation of unlimited additional random strings from the same distribution, which can act as alternative canaries for audits and as same-distribution held-out data for dataset inference. Our evaluation highlights that indeed, using NIDs, we can facilitate post-hoc differential privacy auditing without any retraining and enable dataset inference for any suspect dataset containing NIDs without the need for a private non-member held-out dataset.

cs.LG↗

arXiv2026

MGI: Member vs Generated Inference

As generative models increasingly produce samples that are indistinguishable from human-created content, it becomes difficult to determine whether a given data point was part of a model's natural training set or was generated by the model itself, especially when models memorize and reproduce training data. We formalize this challenge as Member vs Generated Inference (MGI): given a sample and a target generative model, infer whether the sample is a true training member or a generated output of that model. Focusing on image generation, we show that existing membership inference methods systematically misclassify generated samples as training members, while attribution-based methods often misclassify true members as generated. This failure arises because both approaches rely on likelihood-related signals that are similarly elevated for training examples and for the model's own outputs. To address MGI, we propose Data Circuit Breaker (DCB), a three-stage method that combines complementary signals from a generative model's autoencoder and latent generator to distinguish training members from generated samples. Across multiple generative models, including image autoregressive and diffusion models, DCB consistently addresses the shortcomings of membership inference and attribution methods, remains effective even when models reproduce near-duplicates of training samples, and generalizes to challenging model derivative settings in which new models are trained on generated data.

cs.LG↗

arXiv2026

Data Provenance for Image Auto-Regressive Generation

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.

cs.CV↗

arXiv2026

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees. However, its practical effectiveness remains unclear, partly due to LLM pretraining, where overlaps and interdependencies with adaptation data can undermine privacy despite DP efforts. To analyze this issue in practice, we investigate privacy risks under DP adaptations in LLMs using state-of-the-art attacks such as robust membership inference and canary data extraction. We benchmark these risks by systematically varying the adaptation data distribution, from exact overlaps with pretraining data, through in-distribution (IID) cases, to entirely out-of-distribution (OOD) examples. Additionally, we evaluate how different adaptation methods and different privacy regimes impact the vulnerability. Our results show that distribution shifts strongly influence privacy vulnerability: the closer the adaptation data is to the pretraining distribution, the higher the practical privacy risk at the same theoretical guarantee, even without direct data overlap. We find that parameter-efficient fine-tuning methods, such as LoRA, achieve the highest empirical privacy protection for OOD data. Our benchmark identifies key factors for achieving practical privacy in DP LLM adaptation, providing actionable insights for deploying customized models in sensitive settings. Looking forward, we propose a structured framework for holistic privacy assessment beyond adaptation privacy, to identify and evaluate risks across the full pretrain-adapt pipeline of LLMs.

cs.LG↗

arXiv2026

ADAGE: Active Defenses Against GNN Extraction

Graph Neural Networks (GNNs) achieve high performance in various real-world applications, such as drug discovery, traffic states prediction, and recommendation systems. The fact that building powerful GNNs requires a large amount of training data, powerful computing resources, and human expertise turns the models into lucrative targets for model stealing attacks. Prior work has revealed that the threat vector of stealing attacks against GNNs is large and diverse, as an attacker can leverage various heterogeneous signals ranging from node labels to high-dimensional node embeddings to create a local copy of the target GNN at a fraction of the original training costs. This diversity in the threat vector renders the design of effective and general defenses challenging and existing defenses usually focus on one particular stealing setup. Additionally, they solely provide means to identify stolen model copies rather than preventing the attack. To close this gap, we propose the first and general Active Defense Against GNN Extraction (ADAGE). ADAGE builds on the observation that stealing a model's full functionality requires highly diverse queries to leak its behavior across the input space. Our defense monitors this query diversity and progressively perturbs outputs as the accumulated leakage grows. In contrast to prior work, ADAGE can prevent stealing across all common attack setups. Our extensive experimental evaluation using six benchmark datasets, four GNN models, and three types of adaptive attackers shows that ADAGE penalizes attackers to the degree of rendering stealing impossible, whilst preserving predictive performance on downstream tasks. ADAGE, thereby, contributes towards securely sharing valuable GNNs in the future.

cs.CR↗

arXiv2026

Finding DoRI: Discovery of Retained Images in Diffusion Models

Text-to-image diffusion models (DMs) have achieved remarkable success in image generation. However, concerns about data privacy and intellectual property remain due to their potential to inadvertently memorize and replicate training data. Recent mitigation efforts have focused on identifying and pruning weights responsible for triggering verbatim training data replication, based on the assumption that memorization can be localized. We challenge this assumption and demonstrate that, even after such pruning, small perturbations to the text embeddings of previously mitigated prompts can re-trigger data replication, revealing the fragility of such methods. Our further analysis then provides multiple indications that memorization is indeed \textit{not} inherently local: (1) replication triggers for memorized images are distributed throughout text embedding space; (2) embeddings yielding the same replicated image produce divergent model activations; and (3) different pruning methods identify inconsistent sets of memorization-related weights for the same image. Finally, we show that bypassing the locality assumption enables more robust mitigation through adversarial fine-tuning. These findings provide new insights into the fundamental nature of memorization in text-to-image DMs and inform the future development of more reliable mitigation methods against DM memorization.

cs.CV↗

arXiv2026

Privacy Attacks on Image AutoRegressive Models

Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion models (DMs) in image quality (FID: 1.48 vs. 1.58) while allowing for a higher generation speed. However, the privacy risks associated with IARs remain unexplored, raising concerns regarding their responsible deployment. To address this gap, we conduct a comprehensive privacy analysis of IARs, comparing their privacy risks to the ones of DMs as reference points. Concretely, we develop a novel membership inference attack (MIA) that achieves a remarkably high success rate in detecting training images (with True Positive Rate at False Positive Rate = 1% of 94.57% vs. 6.38% for DMs with comparable attacks). We leverage our novel MIA to provide dataset inference (DI) for IARs, and show that it requires as few as 4 samples to detect dataset membership (compared to 200 for DI in DMs), confirming a higher information leakage in IARs. Finally, we are able to extract hundreds of training data points from an IAR (e.g., 698 from VAR-\textit{d}30). Our results suggest a fundamental privacy-utility trade-off: while IARs excel in image generation quality and speed, they are \textit{empirically} significantly more vulnerable to privacy attacks compared to DMs that achieve similar performance. We release the code at https://github.com/sprintml/privacy_attacks_against_iars for reproducibility.

cs.CV↗

arXiv2026

SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation

We propose SERUM: an intriguingly simple yet highly effective method for marking images generated by diffusion models (DMs). We only add a unique watermark noise to the initial diffusion generation noise and train a lightweight detector to identify watermarked images, simplifying and unifying the strengths of prior approaches. SERUM provides robustness against any image augmentations or watermark removal attacks and is extremely efficient, all while maintaining negligible impact on image quality. In contrast to prior approaches, which are often only resilient to limited perturbations and incur significant training, injection, and detection costs, our SERUM achieves remarkable performance, with the highest true positive rate (TPR) at a 1% false positive rate (FPR) in most scenarios, along with fast injection and detection and low detector training overhead. Its decoupled architecture also seamlessly supports multiple users by embedding individualized watermarks with little interference between the marks. Overall, our method provides a practical solution to mark outputs from DMs and to reliably distinguish generated from natural images.

cs.CV↗

arXiv2026

Conditioned Activation Transport for T2I Safety Steering

Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inference-time intervention, we observe that linear activation steering frequently degrades image quality when applied to benign prompts. To address this trade-off, we first construct SafeSteerDataset, a contrastive dataset containing 2300 safe and unsafe prompt pairs with high cosine similarity. Leveraging this data, we propose Conditioned Activation Transport (CAT), a framework that employs a geometry-based conditioning mechanism and nonlinear transport maps. By conditioning transport maps to activate only within unsafe activation regions, we minimize interference with benign queries. We validate our approach on two state-of-the-art architectures: Z-Image and Infinity. Experiments demonstrate that CAT generalizes effectively across these backbones, significantly reducing Attack Success Rate while maintaining image fidelity compared to unsteered generations. Warning: This paper contains potentially offensive text and images.

cs.CV↗

arXiv2026

Precise Parameter Localization for Textual Generation in Diffusion Models

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$% of diffusion models' parameters, all contained in attention layers, influence the generation of textual content within the images. Building on this observation, we improve textual generation efficiency and performance by targeting cross and joint attention layers of diffusion models. We introduce several applications that benefit from localizing the layers responsible for textual content generation. We first show that a LoRA-based fine-tuning solely of the localized layers enhances, even more, the general text-generation capabilities of large diffusion models while preserving the quality and diversity of the diffusion models' generations. Then, we demonstrate how we can use the localized layers to edit textual content in generated images. Finally, we extend this idea to the practical use case of preventing the generation of toxic text in a cost-free manner. In contrast to prior work, our localization approach is broadly applicable across various diffusion model architectures, including U-Net (e.g., SDXL and DeepFloyd IF) and transformer-based (e.g., Stable Diffusion 3), utilizing diverse text encoders (e.g., from CLIP to the large language models like T5). Project page available at https://t2i-text-loc.github.io/.

cs.CV↗

arXiv2026

Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning

In machine learning, curation is used to select the most valuable data for improving both model accuracy and computational efficiency. Recently, curation has also been explored as a solution for private machine learning: rather than training directly on sensitive data, which is known to leak information through model predictions, the private data is used only to guide the selection of useful public data. The resulting model is then trained solely on curated public data. It is tempting to assume that such a model is privacy-preserving because it has never seen the private data. Yet, we show that without further protection, curation pipelines can still leak private information. Specifically, we introduce novel attacks against popular curation methods, targeting every major step: the computation of curation scores, the selection of the curated subset, and the final trained model. We demonstrate that each stage reveals information about the private dataset and that even models trained exclusively on curated public data leak membership information about the private data that guided curation. These findings highlight the previously overlooked inherent privacy risks of data curation and show that privacy assessment must extend beyond the training procedure to include the data selection process. Our differentially private adaptations of curation methods effectively mitigate leakage, indicating that formal privacy guarantees for curation are a promising direction.

cs.LG↗

arXiv2026

Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images

State-of-the-art Diffusion Models (DMs) produce highly realistic images. While prior work has successfully mitigated Not Safe For Work (NSFW) content in the visual domain, we identify a novel threat: the generation of NSFW text embedded within images. This includes offensive language, such as insults, racial slurs, and sexually explicit terms, posing significant risks to users. We show that all state-of-the-art DMs (e.g., SD3, SDXL, Flux, DeepFloyd IF) are vulnerable to this issue. Through extensive experiments, we demonstrate that existing mitigation techniques, effective for visual content, fail to prevent harmful text generation while substantially degrading benign text generation. As an initial step toward addressing this threat, we introduce a novel fine-tuning strategy that targets only the text-generation layers in DMs. Therefore, we construct a safety fine-tuning dataset by pairing each NSFW prompt with two images: one with the NSFW term, and another where that term is replaced with a carefully crafted benign alternative while leaving the image unchanged otherwise. By training on this dataset, the model learns to avoid generating harmful text while preserving benign content and overall image quality. Finally, to advance research in the area, we release ToxicBench, an open-source benchmark for evaluating NSFW text generation in images. It includes our curated fine-tuning dataset, a set of harmful prompts, new evaluation metrics, and a pipeline that assesses both NSFW-ness and text and image quality. Our benchmark aims to guide future efforts in mitigating NSFW text generation in text-to-image models, thereby contributing to their safe deployment.

cs.CV↗

arXiv2026

Exploring the limits of strong membership inference attacks on large language models

State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a result, prior research has either relied on weaker attacks that avoid training references (e.g., fine-tuning attacks), or on stronger attacks applied to small models and datasets. However, weaker attacks have been shown to be brittle and insights from strong attacks in simplified settings do not translate to today's LLMs. These challenges prompt an important question: are the limitations observed in prior work due to attack design choices, or are MIAs fundamentally ineffective on LLMs? We address this question by scaling LiRA--one of the strongest MIAs--to GPT-2 architectures ranging from 10M to 1B parameters, training references on over 20B tokens from the C4 dataset. Our results advance the understanding of MIAs on LLMs in four key ways. While (1) strong MIAs can succeed on pre-trained LLMs, (2) their effectiveness, remains limited (e.g., AUC<0.7) in practical settings. (3) Even when strong MIAs achieve better-than-random AUC, aggregate metrics can conceal substantial per-sample MIA decision instability: due to training randomness, many decisions are so unstable that they are statistically indistinguishable from a coin flip. Finally, (4) the relationship between MIA success and related LLM privacy metrics is not as straightforward as prior work has suggested.

cs.CR↗