Privacy

State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarantees remains challenging. We introduce a Gaussian Differential Privacy (GDP)-based auditing framework that measures privacy via the full false-positive/false-negative tradeoff. Applied to MST and AIM under worst-case settings, our method provides the first tight audits in the strong-privacy regime. For $(ε,δ)=(1,10^{-2})$, we obtain $μ_{emp}\approx0.43$ vs. implied $μ=0.45$, showing a small theory-practice gap. Our code is publicly available: https://github.com/sassoftware/dpmm.

Large language model optimization has historically bifurcated into isolated data-centric and model-centric paradigms: the former manipulates involved samples through selection, augmentation, or poisoning, while the latter tunes model weights via masking, quantization, or low-rank adaptation. This paper establishes a unified \emph{data-parameter correspondence} revealing these seemingly disparate operations as dual manifestations of the same geometric structure on the statistical manifold $\mathcal{M}$. Grounded in the Fisher-Rao metric $g_{ij}(θ)$ and Legendre duality between natural ($θ$) and expectation ($η$) parameters, we identify three fundamental correspondences spanning the model lifecycle: 1. Geometric correspondence: data pruning and parameter sparsification equivalently reduce manifold volume via dual coordinate constraints; 2. Low-rank correspondence: in-context learning (ICL) and LoRA adaptation explore identical subspaces on the Grassmannian $\mathcal{G}(r,d)$, with $k$-shot samples geometrically equivalent to rank-$r$ updates; 3. Security-privacy correspondence: adversarial attacks exhibit cooperative amplification between data poisoning and parameter backdoors, whereas protective mechanisms follow cascading attenuation where data compression multiplicatively enhances parameter privacy. Extending from training through post-training compression to inference, this framework provides mathematical formalization for cross-community methodology transfer, demonstrating that cooperative optimization integrating data and parameter modalities may outperform isolated approaches across efficiency, robustness, and privacy dimensions.

Users increasingly rely on consumer-facing generative AI (GenAI) for tasks ranging from everyday needs to sensitive use cases. Yet, it remains unclear whether and how existing security and privacy (S&P) communications in GenAI tools shape users' adoption decisions and experiences. Understanding how users seek, interpret, and evaluate S&P information is critical for designing usable transparency that users can trust and act on. We conducted semi-structured interviews and design sessions with 21 U.S. GenAI users. Our findings suggest that available S&P information rarely drove initial adoption in practice, as participants often perceived it as incomplete, ineffective, or not credible. Instead, they relied on rough proxies (e.g., popularity) to infer S&P practices. After adoption, S&P uncertainty constrained participants' willingness to use GenAI tools, especially for high-stakes purposes, and, in some cases, contributed to discontinued use. Participants therefore called for transparency that supports decisions and actions through trustworthy information (e.g., independent evaluations) and usable interfaces (e.g., on-demand disclosure). We categorize participants' desired design practices into five dimensions to facilitate systematic future investigation into best practices. We conclude with recommendations for researchers, designers, and policymakers to improve S&P transparency in consumer-facing GenAI.

We propose PPEDCRF, a calibrated selective perturbation framework that protects \emph{background-based location privacy} in released video frames against gallery-based retrieval attackers. Even after GPS metadata are stripped, an adversary can geolocate a frame by matching its background visual cues to geo-tagged reference imagery; PPEDCRF mitigates this threat by estimating location-sensitive background regions with a dynamic conditional random field (DCRF), rescaling perturbation strength with a normalized control penalty (NCP), and injecting Gaussian noise only inside the inferred regions via a DP-style calibration rule. On a controlled paired-scene retrieval benchmark with eight attacker backbones and three noise seeds, PPEDCRF reduces ResNet18 Top-1 retrieval accuracy from 0.667 to $0.361\pm0.127$ at $σ_0=8$ while preserving $36.14\,$dB PSNR -- an ${\approx}6\,$dB quality advantage over global Gaussian noise. Transfer across the eight-backbone seed-averaged benchmark is broadly supportive (23 of 24 backbone-gallery cells show negative $Δ$), while appendix-scale confirmation identifies MixVPR as a remaining adverse-transfer exception. Matched-operating-point analysis shows that PPEDCRF and global Gaussian noise converge in Top-1 privacy at equal utility, so the practical benefit is spatially concentrated perturbation that preserves higher visual quality at any given noise scale rather than stronger matched-utility privacy. Code: https://github.com/mabo1215/PPEDCRF

Despite the considerable promise of Retrieval-Augmented Generation (RAG), many real-world use cases may create privacy concerns, where the purported utility of RAG-enabled insights comes at the risk of exposing private information to either the LLM or the end user requesting the response. As a potential mitigation, using anonymization techniques to remove personally identifiable information (PII) and other sensitive markers in the underlying data represents a practical and sensible course of action for RAG administrators. Despite a wealth of literature on the topic, no works consider the placement of anonymization along the RAG pipeline, i.e., asking the question, where should anonymization happen? In this case study, we systematically and empirically measure the impact of anonymization at two important points along the RAG pipeline: the dataset and generated answer. We show that differences in privacy-utility trade-offs can be observed depending on where anonymization took place, demonstrating the significance of privacy risk mitigation placement in RAG.

The deployment of Large Language Models in agentic, multi-turn conversational settings has introduced a class of privacy vulnerabilities that existing protection mechanisms are not designed to address. Current approaches to Personally Identifiable Information (PII) masking operate on a per-turn basis, scanning each user message in isolation and replacing detected entities with typed placeholders before forwarding sanitized text to the model. While effective against direct identifier leakage within a single message, these methods are fundamentally stateless and fail to account for the compounding privacy risk that emerges when PII fragments accumulate across conversation turns. A user who separately discloses their name, employer, location, and medical condition across several messages has revealed a fully re-identifiable profile - yet no individual message would trigger a per-turn masker. We formalize this phenomenon as Cumulative PII Exposure (CPE) and propose CAMP (Cumulative Agentic Masking and Pruning), a cross-turn privacy protection framework for multi-turn LLM conversations. CAMP maintains a session-level PII registry, constructs a co-occurrence graph to model combination risk between entity types, computes a CPE score after each turn, and triggers retroactive masking of conversation history when the score crosses a configurable threshold. We evaluate CAMP on four synthetic multi-turn scenarios spanning healthcare, hiring, finance, and general conversation, demonstrating that per-turn baselines expose re-identifiable profiles that CAMP successfully neutralizes while preserving full conversational utility.

Financial institutions face tension between maximizing data utility and mitigating the re-identification risks inherent in traditional anonymization methods. This paper explores Differentially Private (DP) synthetic data as a robust "Privacy by Design" framework to resolve this conflict, ensuring output privacy while satisfying stringent regulatory obligations. We examine two distinct generative paradigms: Direct Tabular Synthesis, which reconstructs high-fidelity joint distributions from raw data, and DP-Seeded Agent-Based Modeling (ABM), which uses DP-protected aggregates to parameterize complex, stateful simulations. While tabular synthesis excels at reflecting static historical correlations for QA testing and business analytics, the DP-Seeded ABM offers a forward-looking "counterfactual laboratory" capable of modeling dynamic market behaviors and black swan events. By decoupling individual identities from data utility, these methodologies eliminate traditional data-clearing bottlenecks, enabling seamless cross-institutional research and compliant decision-making in an evolving regulatory landscape.

The use of synthetic data in machine learning applications and research offers many benefits, including performance improvements through data augmentation and privacy preservation of original samples. This work proposes an efficient synthetic data generation method based on a fully connected neural network that transforms a high-dimensional random Gaussian distribution to approximate a target real-world dataset. The proposed solution combines data preprocessing designed for tabular data with distribution modeling and PCA dimensionality reduction to further enhance data privacy. The work also defines two dedicated randomized loss functions based on Wasserstein distance combined with feature Covariance and a randomized pairwise error reduction loss function. The experiments conducted on 25 diverse tabular real-world datasets confirm that the proposed solution obtains similarity and privacy scores relative to the state-of-the-art generative methods and achieves reference MMD scores orders of magnitude faster than modern deep learning solutions. The experiments involved analyzing distributional similarity, privacy protection, and the utility of synthetic data in classification tasks.

Visual navigation is a fundamental capability of mobile service robots, yet the onboard cameras required for such navigation can capture privacy-sensitive information and raise user privacy concerns. Existing approaches to privacy-preserving navigation-oriented visual perception have largely been driven by technical considerations, with limited grounding in user privacy preferences. In this work, we propose a user-centered approach to designing privacy-preserving visual perception for robot navigation. To investigate how user privacy preferences can inform such design, we conducted two user studies. The results show that users prefer privacy-preserving visual abstractions and capture-time low-resolution preservation mechanisms: their preferred RGB resolution depends both on the desired privacy level and robot proximity during navigation. Based on these findings, we further derive a user-configurable distance-to-resolution privacy policy for privacy-preserving robot visual navigation.

Existing visual privacy benchmarks largely treat privacy as a binary property, labeling images as private or non-private based on visible sensitive content. We argue that privacy is fundamentally compositional. Attributes that are benign in isolation may combine to produce severe privacy violations. We introduce the Compositional Privacy Risk Taxonomy (CPRT), a regulation-aware framework that organizes visual attributes according to standalone identifiability and compositional harm potential. CPRT defines four graded severity levels and is paired with an interpretable scoring function that assigns continuous privacy severity scores. We further construct a taxonomy-aligned dataset of 6.7K images and derive compositional risk scores. By evaluating frontier and open-weight VLMs we find that frontier models align well with compositional severity when provided structured guidance, but systematically underestimate composition-driven risks. Smaller models struggle to internalize graded privacy reasoning. To bridge this gap, we introduce a deployable 8B SFT model that closely matches frontier-level performance on compositional privacy assessment

Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In this paper, we introduce an attribute-based perspective, where we measure privacy protection in terms of comparisons between sets of speaker attributes. First, we analyze privacy impact by calculating speaker uniqueness for ground truth attributes, attributes inferred on the original speech, and attributes inferred on speech protected with standard anonymization. Next, we examine a threat scenario involving only a single utterance per speaker and calculate attack error rates. Overall, we observe that inferred attributes still present a risk despite attribute inference errors. Our research points to the importance of considering both attribute-related threats and protection mechanisms in future voice privacy research.

Large Vision-Language Models (LVLMs) have shown remarkable potential across a wide array of vision-language tasks, leading to their adoption in critical domains such as finance and healthcare. However, their growing deployment also introduces significant security and privacy risks. Malicious actors could potentially exploit these models to extract sensitive information, highlighting a critical vulnerability. Recent studies show that LVLMs often fail to consistently refuse instructions designed to compromise user privacy. While existing work on privacy protection has made meaningful progress in preventing the leakage of sensitive data, they are constrained by limitations in both generalization and non-destructiveness. They often struggle to robustly handle unseen privacy-related queries and may inadvertently degrade a model's performance on standard tasks. To address these challenges, we introduce Neural Gate, a novel method for mitigating privacy risks through neuron-level model editing. Our method improves a model's privacy safeguards by increasing its rate of refusal for privacy-related questions, crucially extending this protective behavior to novel sensitive queries not encountered during the editing process. Neural Gate operates by learning a feature vector to identify neurons associated with privacy-related concepts within the model's representation of a subject. This localization then precisely guides the update of model parameters. Through comprehensive experiments on MiniGPT and LLaVA, we demonstrate that our method significantly boosts the model's privacy protection while preserving its original utility. The code is available at https://github.com/Xiangkui-Cao/Neural-Gate.

Theoretical and applied research into privacy encompasses an incredibly broad swathe of differing approaches, emphases and aims. This work introduces a novel quantitative notion of privacy that is both contextual and specific. Building on and extending ideas from statistical disclosure control and differential privacy, our aim is to model the implications of a disclosure decision in an adversarial setting. Our definition relies on concepts inherent to standard Bayesian decision theory, while departing from them in several important respects. In particular, (i) inference about the data itself becomes meaningful and (ii) the party controlling the release of sensitive information should make disclosure decisions from the prior viewpoint, rather than conditional on the data, which is a feature shared with Bayesian design. Illuminating toy examples are exploited towards highlighting the specificities of the method.

Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of privacy-induced utility loss unclear. We introduce Differential Privacy Representation Geometry for Medical Imaging (DP-RGMI), a framework that interprets DP as a structured transformation of representation space and decomposes performance degradation into encoder geometry and task-head utilization. Geometry is quantified by representation displacement from initialization and spectral effective dimension, while utilization is measured as the gap between linear-probe and end-to-end utility. Across over 594,000 images from four chest X-ray datasets and multiple pretrained initializations, we show that DP is consistently associated with a utilization gap even when linear separability is largely preserved. At the same time, displacement and spectral dimension exhibit non-monotonic, initialization- and dataset-dependent reshaping, indicating that DP alters representation anisotropy rather than uniformly collapsing features. Correlation analysis reveals that the association between end-to-end performance and utilization is robust across datasets but can vary by initialization, while geometric quantities capture additional prior- and dataset-conditioned variation. These findings position DP-RGMI as a reproducible framework for diagnosing privacy-induced failure modes and informing privacy model selection.

Privacy preserving machine learning deployments in sensitive deep learning applications; from medical imaging to autonomous systems; increasingly require combining multiple techniques. Yet, practitioners lack systematic guidance to assess the synergistic and non-additive interactions of these hybrid configurations, relying instead on isolated technique analysis that misses critical system level interactions. We introduce PrivacyBench, a benchmarking framework that reveals striking failures in privacy technique combinations with severe deployment implications. Through systematic evaluation across ResNet18 and ViT models on medical datasets, we uncover that FL + DP combinations exhibit severe convergence failure, with accuracy dropping from 98% to 13% while compute costs and energy consumption substantially increase. In contrast, FL + SMPC maintains near-baseline performance with modest overhead. Our framework provides the first systematic platform for evaluating privacy-utility-cost trade-offs through automated YAML configuration, resource monitoring, and reproducible experimental protocols. PrivacyBench enables practitioners to identify problematic technique interactions before deployment, moving privacy-preserving computer vision from ad-hoc evaluation toward principled systems design. These findings demonstrate that privacy techniques cannot be composed arbitrarily and provide critical guidance for robust deployment in resource-constrained environments.

We consider the privacy amplification properties of a sampling scheme in which a user's data isused in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps. This sampling scheme has been recently applied in the context of differentially private optimization (Chua et al., 2024a; Choquette-Choo et al., 2025) and communication-efficient high-dimensional private aggregation (Asi et al., 2026), where it was shown to have utility advantages over the standard Poisson sampling. Theoretical analyses of this sampling scheme (Feldman & Shenfeld, 2025; Dong et al., 2025) lead to bounds that are close to those of Poisson sampling, yet still have two significant shortcomings. First, in many practical settings, the resulting privacy parameters are not tight due to the approximation steps in the analysis. Second, the computed parameters are either the hockey stick or Renyi divergence, both of which introduce overheads when used in privacy loss accounting. In this work, we demonstrate that the privacy loss distribution (PLD) of random allocation applied to any differentially private algorithm can be computed efficiently. When applied to the Gaussian mechanism, our results demonstrate that the privacy-utility trade-off for random allocation is at least as good as that of Poisson subsampling. In particular, random allocation is better suited for training via DP-SGD. To support these computations, our work develops new tools for general privacy loss accounting based on a notion of PLD realization. This notion allows us to extend accurate privacy loss accounting to subsampling which previously required manual noise-mechanism-specific analysis.

Graph-structured data underpin a wide spectrum of modern applications, yet their multiple sensitive attributes are not isolated but deeply coupled with graph topology. This coupling facilitates intersectional privacy leakage through attribute inference attacks (AIAs). Existing AIAs predominantly assume adversaries with two capabilities: (I) access to either auxiliary data sampled from the same distribution as the target or partial training records, and (II) the ability to repeatedly query the victim model. In reality, however, these assumptions are often impractical due to stringent data protection regulations, prohibitive query budgets, and heightened detection risks. Moreover, as prior attacks are designed to infer a single sensitive attribute at a time, they fail to simultaneously recover multiple attributes and thus underestimate overall privacy risks arising from cross-attribute dependencies. More critically, they obscure a systemic blind spot: \textbf{auxiliary graphs alone are sufficient to expose multiple sensitive attributes in the target graph.} This threat persists even under distribution shifts, enabling stealthy offline attacks without any model interactions. To investigate this unexplored vulnerability, we introduce \textbf{Taipan, the first query-free framework for multiple sensitive attribute inference attacks on graphs (G-MSAIAs).} Taipan incorporates \emph{Hierarchical Attack Knowledge Routing} to capture intricate inter-attribute correlations, and \emph{Prompt-guided Attack Prototype Refinement} to mitigate distribution shifts between auxiliary and target graphs. Extensive experiments on diverse real-world graph datasets demonstrate that Taipan consistently achieves strong attack performance across same-, similar-, and out-of-distribution settings, and remains effective under partial label coverage or even rigorous privacy guarantees.

Privacy preservation is critical in many high-stakes domains such as medicine and finance, where sensitive data must be analyzed without compromising individual confidentiality. At the same time, these applications often involve datasets with inherent missing values due to non-response or data corruption for example. Missing data is traditionally analyzed through its impact on statistical efficiency and model performance. In fact, it reduces the information available to analysts and can degrade the final utility of the model. In this work, we take an alternative approach and study missing data through the lens of privacy preservation. Intuitively, when features are missing, less information is revealed about individuals, suggesting that data missingness could inherently enhance privacy. We formalize this intuition within a novel framework that integrates missing data into differential privacy. In essence, our approach accounts for the de facto missingness in the data to refine existing privacy guarantees without modifying the underlying mechanism. Using this framework, we show for the first time that missing data can induce inherent privacy amplification for differentially private algorithms, highlighting a previously overlooked interaction between missing data and formal privacy guarantees..

Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We introduce AlienLM, a deployable API-only \cradd{exposure-reduction layer that reduces plaintext exposure} by translating text into an Alien Language via a vocabulary-scale bijection, enabling lossless recovery on the client side. Using only standard fine-tuning APIs, Alien Adaptation Training (AAT) adapts target models to operate directly on alienized inputs. Across four LLM backbones and seven benchmarks, AlienLM retains over 81% of plaintext-oracle performance on average, substantially outperforming random-bijection and character-level baselines. Under adversaries with access to model weights, corpus statistics, and learning-based inverse translation, recovery attacks reconstruct fewer than 0.22% of alienized tokens. Our results demonstrate a practical pathway for \cradd{privacy-aware} LLM deployment under API-only access, substantially reducing plaintext exposure while maintaining task performance. Code and data are available at https://github.com/KimJaehee0725/AlienLM.

As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emerges: the model is expected to distinguish between users to manage information flow appropriately. Without this capability, an SLM could reveal one user's confidential schedule to another, a privacy failure we term interactional privacy. Thus, the ability to generate speaker-aware responses becomes essential for SLM safe deployment. Current SLM benchmarks test dialogue ability but overlook speaker identity. Multi-speaker benchmarks check who said what without assessing whether SLMs adapt their responses. Privacy benchmarks focus on globally sensitive data (e.g., bank passwords) while neglecting contextual privacy-sensitive information (e.g., a user's private appointment). To address this gap, we introduce VoxPrivacy, the first benchmark designed to evaluate interactional privacy in SLMs. VoxPrivacy spans three tiers of increasing difficulty, from following direct secrecy commands to proactively protecting privacy. Our evaluation of nine SLMs on a 32-hour bilingual dataset reveals a widespread vulnerability: most open-source models perform close to random chance (around 50% accuracy) on conditional privacy decisions, while even strong closed-source systems fall short on proactive privacy inference. We further validate these findings on Real-VoxPrivacy, a human-recorded subset, confirming that failures observed on synthetic data persist in real speech. Finally, we demonstrate a viable path forward: by fine-tuning on a new 4,000-hour training set, we improve privacy-preserving abilities while maintaining robustness. To support future work, we release the VoxPrivacy benchmark, the large-scale training set, and the fine-tuned model to foster the development of safer and more context-aware SLMs.

Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities are enabling transformative applications in domains spanning from personal assistant, financial, and legal domains. While these systems can substantially improve productivity and service quality, effective agency typically requires access to sensitive personal or organizational information. However, this access introduces critical inference-time privacy risks, specifically regarding contextually appropriate information disclosure. While recent studies highlight the inability of agentic LLMs to consistently adhere to privacy norms, existing defenses often rely on auxiliary LLM-based monitors. However, these defenses are expensive and offer limited protection against attacks that are robust to semantic censorship. To contrast this background, this paper proposes a notion of privacy filters based on activation probing. We show that these filters are both computationally efficient and effective for both single-turn and multi-turn conversational settings. Furthermore, this work provides the first systematic investigation into probing model internals across a conversation trajectory, moving beyond static, single-prompt analysis to capture the evolving state of privacy-sensitive interactions.

Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i.e., text written under the influence of alcohol, as a driver for safety failures in large language models (LLMs). We investigate three mechanisms for inducing drunk language in LLMs: persona-based prompting, causal fine-tuning, and reinforcement-based post-training. When evaluated on 5 LLMs, we observe a higher susceptibility to jailbreaking on JailbreakBench (even in the presence of defences) and privacy leaks on ConfAIde, where both benchmarks are in English, as compared to the base LLMs as well as previously reported approaches. Via a robust combination of manual evaluation and LLM-based evaluators and analysis of error categories, our findings highlight a correspondence between human-intoxicated behaviour, and anthropomorphism in LLMs induced with drunk language. The simplicity and efficiency of our drunk language inducement approaches position them as potential counters for LLM safety tuning, highlighting significant risks to LLM safety.

Large language models (LLMs) are increasingly used to simulate decision-making tasks involving personal data sharing, where privacy concerns and prosocial motivations can push choices in opposite directions. Existing evaluations often measure privacy-related attitudes or sharing intentions in isolation, which makes it difficult to determine whether a model's expressed values jointly predict its downstream data-sharing actions as in real human behaviors. We introduce a context-based assessment protocol that sequentially administers standardized questionnaires for privacy attitudes, prosocialness, and acceptance of data sharing within a bounded, history-carrying session. To evaluate value-action alignments under competing attitudes, we use multi-group structural equation modeling (MGSEM) to identify relations from privacy concerns and prosocialness to data sharing. We propose Value-Action Alignment Rate (VAAR), a human-referenced directional agreement metric that aggregates path-level evidence for expected signs. Across multiple LLMs, we observe stable but model-specific Privacy-PSA-AoDS profiles, and substantial heterogeneity in value-action alignment.

Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to share private information (e.g., contact details, health records). To evaluate LLMs' ability to identify and redact such information, prior work introduced real-life, scenario-based benchmarks (e.g., ConfAIde, PrivacyLens) and found that LLMs can leak private information in complex scenarios. However, these evaluations relied on proxy LLMs to judge the helpfulness and privacy-preservation quality of LLM responses, rather than directly measuring users' perceptions. To understand how users perceive the helpfulness and privacy-preservation quality of LLM responses to privacy-sensitive scenarios, we conducted a user study ($n=94$) using 90 PrivacyLens scenarios. We found that users had low agreement with each other when evaluating identical LLM responses. In contrast, five proxy LLMs reached high agreement, yet each proxy LLM had low correlation with users' evaluations. These results indicate that proxy LLMs cannot accurately estimate users' wide range of perceptions of utility and privacy in privacy-sensitive scenarios. We discuss the need for more user-centered studies to measure LLMs' ability to help users while preserving privacy, and for improving alignment between LLMs and users in estimating perceived privacy and utility.

Policymakers enact and revise privacy laws expecting meaningful benefits for their people in practice. While scholarship has measured the real-world impact of some privacy regulations-the EU and California most notably-limited empirical evidence exists for many of the more than 140 countries that have implemented some form of privacy legislation. Switzerland, a multilingual country bordered almost entirely by EU states, is one such example. This paper analyzes the extent to which a 2023 alignment of Swiss privacy law with EU privacy regulation affected website privacy policies in Switzerland. To address Switzerland's unique multilingual culture, we develop an LLM-based pipeline that extracts legally relevant information as document-level labels in a single inference without requiring translation. On a benchmark of 120 expert-annotated privacy policies in German, French, Italian, and English, our pipeline achieves F1 scores above 0.90 for most pairs of languages and legally relevant disclosures. Applying this pipeline to privacy policies we collected from more than 35,000 Swiss- and EU-facing websites before and after the 2023 privacy law revision, we find significant increases in both mandatory and voluntary disclosures of data subject rights among Swiss privacy policies. In exploring the mechanisms driving increased disclosure rates, we discover heavy use of automated privacy policy generators and find that generated policies are associated with up to 15 percentage points higher disclosure rates. These results provide large-scale empirical evidence of how regulatory change and novel drafting technologies impact the content of privacy policies in a unique multilingual environment.

Environmental sound recordings often contain intelligible speech, raising privacy concerns that limit analysis, sharing and reuse of data. In this paper, we introduce a method that renders speech unintelligible while preserving both the integrity of the acoustic scene, and the overall audio quality. Our approach involves reversing waveform segments to distort speech content. This process is enhanced through a voice activity detection and speech separation pipeline, which allows for more precise targeting of speech. In order to demonstrate the effectivness of the proposed approach, we consider a three-part evaluation protocol that assesses: 1) speech intelligibility using Word Error Rate (WER), 2) sound sources detectability using Sound source Classification Accuracy-Drop (SCAD) from a widely used pre-trained model, and 3) audio quality using the Fréchet Audio Distance (FAD), computed with our reference dataset that contains unaltered speech. Experiments on this simulated evaluation dataset, which consists of linear mixtures of speech and environmental sound scenes, show that our method achieves satisfactory speech intelligibility reduction (97.9% WER), minimal degradation of the sound sources detectability (2.7% SCAD), and high perceptual quality (FAD of 1.40). An ablation study further highlights the contribution of each component of the pipeline. We also show that incorporating random splicing to our speech content privacy enforcement method can enhance the algorithm's robustness to attempt to recover the clean speech, at a slight cost of audio quality.

Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them. Machine unlearning has emerged as a practical means to facilitate model forgetting of data instances seen during training. Although some existing machine unlearning methods guarantee exact forgetting, they are typically costly in computational terms. On the other hand, more affordable methods do not offer forgetting guarantees and are applicable only to specific ML models. In this paper, we present \emph{efficient unlearning with privacy guarantees} (EUPG), a novel machine unlearning framework that offers formal privacy guarantees to individuals whose data are being unlearned. EUPG involves pre-training ML models on data protected using privacy models, and it enables {\em efficient unlearning with the privacy guarantees offered by the privacy models in use}. Through empirical evaluation on four heterogeneous data sets protected with $k$-anonymity and $ε$-differential privacy as privacy models, our approach demonstrates utility and forgetting effectiveness comparable to those of exact unlearning methods, while significantly reducing computational and storage costs. Our code is available at https://github.com/najeebjebreel/EUPG.

Accurate modeling of subjective phenomena such as emotion expression requires data annotated with authors' intentions. Commonly such data is collected by asking study participants to donate and label genuine content produced in the real world, or create content fitting particular labels during the study. Asking participants to create content is often simpler to implement and presents fewer risks to participant privacy than data donation. However, it is unclear if and how study-created content may differ from genuine content, and how differences may impact models. We collect study-created and genuine multimodal social media posts labeled for emotion and compare them on several dimensions, including model performance. We find that compared to genuine posts, study-created posts are longer, rely more on their text and less on their images for emotion expression, and focus more on emotion-prototypical events. The samples of participants willing to donate versus create posts are demographically different. Study-created data is valuable to train models that generalize well to genuine data, but realistic effectiveness estimates require genuine data.

As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle privacy-sensitive content is thus essential to protect users. To this end, we conduct a comprehensive evaluation of twelve state-of-the-art VLMs and identify limitations in their understanding of visual privacy. However, existing privacy-related datasets often suffer from label inconsistencies, limiting their reliability. To address this, we introduce two compact, high-quality benchmarks, PrivBench and PrivBench-H, that focus on commonly recognised visual privacy categories aligned with the General Data Protection Regulation (GDPR). Additionally, we present PrivTune, an instruction-tuning dataset specifically curated to improve privacy sensitivity. We obtain multiple Privacy VLMs by fine-tuning off-the-shelf VLMs on only a few hundred samples from PrivTune, which leads to substantial gains on all benchmarks, surpassing even GPT-4, while maintaining strong performance on other tasks. Our findings show that privacy-awareness in VLMs can be substantially improved with minimal data and careful dataset design, setting the stage for safer, more privacy-aligned AI systems.

In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory writes, tool arguments, OCR-derived text, and logs, and every downstream copy inherits what the first write contained. Existing de-identification pipelines protect document boundaries but not this cross-stage surface. We present BodhiPromptShield, a policy-aware mediation layer that detects sensitive spans before they propagate, replaces each with a typed placeholder, a semantic abstraction, or a secure symbolic token under a configured policy, and defers restoration to authorized execution boundaries. We evaluate it under one protocol against Presidio, Casper-style sanitization, an LLM sanitizer, and transformer and learned detectors, on 300 AI4Privacy documents, 493 PrivacyLens trajectories, 200 PrivacyLens tasks scored by that benchmark's own judge, and AgentDojo tasks under injection. Three findings result. Identifier propagation is controllable: residual exposure falls to 7.4% on AI4Privacy and 1.8% on PrivacyLens, and exact identifiers in an agent's final action fall from 13.7% to 2.1-3.1%. Restoration timing governs what every stage upstream of the authorized boundary sees: deferring it leaves 1.6% of protected values readable in the released context against 51.0%, and 2.7% against 4.8% in what the agent emits, for 0.11 helpfulness points. Measuring factual disclosure is harder: a word-overlap metric and an LLM judge both report that mediation leaves facts intact, and both disagree with blind human annotation (kappa = 0.25 and 0.09). The human labels reverse that: inferability falls from 100% to 24-53% under mediation, so semantic-leakage measures need human validation before they are trusted. These are systems results on English text with open-weight models, not formal guarantees.

This paper explores the use of linear aggregation to protect the privacy of sensitive training labels through the concept of \emph{label differential privacy} (label-DP) while maintaining regression task utility. Our key finding is that weighted linear aggregation of training instances with i.i.d. $N(0, 1)$ weights can achieve $(\varepsilon, \delta)$-label-DP with $m = O\left(n/(\log(1/\delta))\right)$. Unlike prior methods, our approach relies on the minimum linear regression loss rather than the minimum singular value of the data matrix, resulting in better practical bounds on real datasets. We also examine real-world mechanisms involving disjoint sets or \textit{bags} of instances. We demonstrate that aggregating labels from sub-sampled disjoint $k$-sized bags using i.i.d. $N(0,1)$ weights achieves $(\varepsilon,\delta)$-label-DP with $k \geq \Omega\left(\left((1/\varepsilon)\log\left(1/\delta\right)\right)^2\right)$. In both scenarios, the optimal linear mse-regressor on the aggregated data approximates the original dataset's optimum with high probability, without needing additive label noise. Furthermore, we show that adding $N(0,1)$ noise to any constant fraction of labels allows for similar label-DP guarantees when aggregating labels over random disjoint bags, while preserving the utility of Lipschitz-bounded neural mse-regression tasks.

The pandemic in 2020 and 2021 had enormous economic and societal consequences, and studies show that contact tracing algorithms can be key in the early containment of the virus. While large strides have been made towards more effective contact tracing algorithms, we argue that privacy concerns currently hold deployment back. The essence of a contact tracing algorithm constitutes the communication of a risk score. Yet, it is precisely the communication and release of this score to a user that an adversary can leverage to gauge the private health status of an individual. We pinpoint a realistic attack scenario and propose a contact tracing algorithm with differential privacy guarantees against this attack. The algorithm is tested on the two most widely used agent-based COVID19 simulators and demonstrates superior performance in a wide range of settings. Especially for realistic test scenarios and while releasing each risk score with epsilon=1 differential privacy, we achieve a two to ten-fold reduction in the infection rate of the virus. To the best of our knowledge, this presents the first contact tracing algorithm with differential privacy guarantees when revealing risk scores for COVID19.

In human-centric Cyber-Physical Systems (CPS), personalized Deep Reinforcement Learning (DRL) agents must share fine-grained control actions with cloud services, exposing sensitive private states to inference attacks by honest-but-curious adversaries. Static privacy models fail to address the dynamic nature of human interactions. This paper introduces PEARL (Personalized Early-exit Adaptive Reinforcement Learning), a novel framework that addresses this challenge through structural privacy control rather than data perturbation. PEARL deploys a dual-path Early-Exit Deep Q-Network (EE-DQN) at the edge, using Mutual Information (MI) between private states and observable actions to train per-branch binary labels: Utility Confidence Labels (UCL), verifying action quality, and Privacy Confidence Labels (PCL), verifying MI leakage remains below a user-defined threshold. At inference, PEARL selects the shallowest exit branch satisfying both UCL and PCL, structurally limiting shared action descriptive power without noise injection. An MI-based feedback loop tracks behavioral drift and triggers retraining when privacy-utility profiles shift, ensuring long-term robustness. Validated on a personalized smart-home HVAC system and a VR smart classroom, PEARL reduces adversarial state-inference accuracy by 25.67% on average with a controlled 10-16% utility cost, establishing a practical, dynamically enforceable privacy-utility tradeoff.

Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-application access is useful, but it also creates a privacy risk that has been largely overlooked: when an agent works in one context, it can pull in information from another that is inappropriate in that context. Hence, we introduce AgentCIBench, an evaluation harness that turns this risk into executable, deterministically scored scenarios. We target three common failure modes in CUAs: visual co-location, where the agent pulls in prohibited items that sit next to the task target in the UI; task-ambiguity overshare, where the agent dumps dense personal state in response to an under-specified prompt; and recipient misalignment, where the agent sends content to an addressee for whom it is inappropriate. We evaluate 15 frontier agents and find a surprisingly high failure rate: 11 of 15 leak on more than 50% of scenarios, with an average leakage of 67.9%, and the same failures persist when agents act end-to-end in the environment to complete the task. We release AgentCIBench to encourage the development of safer computer-use agents and position contextual disclosure testing as a pre-deployment safety check.

The COVID19 pandemic had enormous economic and societal consequences. Contact tracing is an effective way to reduce infection rates by detecting potential virus carriers early. However, this was not generally adopted in the recent pandemic, and privacy concerns are cited as the most important reason. We substantially improve the privacy guarantees of the current state of the art in decentralized contact tracing. Whereas previous work was based on statistical inference only, we augment the inference with a learned neural network and ensure that this neural augmentation satisfies differential privacy. In a simulator for COVID19, even at epsilon=1 per message, this can significantly improve the detection of potentially infected individuals and, as a result of targeted testing, reduce infection rates. This work marks an important first step in integrating deep learning into contact tracing while maintaining essential privacy guarantees.