Discourse - Private Group Membership Inference via exclude_groups

Discourse 2026.3.0-latest.1, 2026.2.1, and 2026.1.2 contains an information disclosure caused by unauthenticated users observing directory results changes with the excludegroups parameter, letting attackers determine private group membership, exploit requires public access to user directory. id:...

PrivacyRaven

Note: This project is on hiatus. PrivacyRaven is a privacy testing library for deep learning systems. You can use it to determine the susceptibility of a model to different privacy attacks; evaluate privacy preserving machine learning techniques; develop novel privacy metrics and attacks; and...

Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use

Jev turns natural-language questions into typed answers and probabilities with low latency and cost, enabling applications to route requests and select tools. While this interface allows Jev to integrate naturally into application workflows as a decision layer, the security and privacy implicatio...

Leaky Students: Membership Inference against On-Policy Distillation

On-policy distillation OPD trains a student to match a teacher's next-token distributions on student-generated trajectories. However, privileged information supplied to the teacher for OPD training may contain sensitive data. Whether the student leaks private information about the records supplie...

Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models

Text-to-Speech TTS foundation models are increasingly fine-tuned on private datasets to synthesize highly personalized voices, introducing severe privacy risks by exposing both biometric identities and sensitive speech content. Existing black-box membership inference attacks MIAs follow a two-sta...

Mitigating Explanation Leakage in Financial Fraud Detection Systems

Financial fraud detection relies heavily on centralized machine learning models. This creates serious data privacy risks. Federated Learning FL decentralizes data processing, but financial regulations still require models to be transparent. This means using Explainable AI XAI tools such as...

Evaluating Frontier AI Agents As Autonomous Clinical Security Auditors

Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical expertise, specialized tools, and significant time. We present an open evaluation task, built on METR Task Standard v0.3.0, that tests whether frontier ...

On Reliability of Efficient Membership Inference Vulnerability Evaluation

Membership inference attacks MIAs are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MIA vulnerability is often evaluated through false positive rate FPR and true positive rate TPR of a...

AI Security Research Should Better Incentivize Defense Research

This work examines an imbalance in artificial intelligence AI security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratios across subfields, including federated learning, speech...

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

Large Language Models LLMs have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure PDE increase due to the scale and opacity of training datasets. PDE refers to determining whether specif...

Evaluating Differential Privacy against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge

While Federated Learning FL mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks MIAs. This paper presents an empirical evaluation of Differential Privacy DP as a defense mechanism against MIAs in FL, leveraging the environment of the 202...

CVE-2026-32618

Discourse (open-source discussion platform) has a channel membership inference vulnerability affecting versions 2026.1.0-latest to before 2026.1.3, 2026.2.0-latest to before 2026.2.2, and 2026.3.0-latest to before 2026.3.0, where chat user search could reveal channel membership without authorizat...

EUVD-2026-17555

Discourse is an open-source discussion platform. From versions 2026.1.0-latest to before 2026.1.3, 2026.2.0-latest to before 2026.2.2, and 2026.3.0-latest to before 2026.3.0, there is possible channel membership inference from chat user search without authorization. This issue has been patched in...

CVE-2026-32618: Exposure of Sensitive Information to an Unauthorized Actor

Discourse is an open-source discussion platform. From versions 2026.1.0-latest to before 2026.1.3, 2026.2.0-latest to before 2026.2.2, and 2026.3.0-latest to before 2026.3.0, there is possible channel membership inference from chat user search without authorization. This issue has been patched in...

Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

Retrieval-Augmented Generation RAG significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces complex system-level security vulnerabilities. Guided by the R...

LoRA As Oracle

Backdoored and privacy-leaking deep neural networks pose a serious threat to the deployment of machine learning systems in security-critical settings. Existing defenses for backdoor detection and membership inference typically require access to clean reference models, extensive retraining, or...

How Worrying Are Privacy Attacks against Machine Learning?

In several jurisdictions, the regulatory framework on the release and sharing of personal data is being extended to machine learning ML. The implicit assumption is that disclosing a trained ML model entails a privacy risk for any personal data used in training comparable to directly releasing tho...

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

Retrieval-Augmented Generation RAG is an emerging approach in natural language processing that combines large language models LLMs with external document retrieval to produce more accurate and grounded responses. While RAG has shown strong potential in reducing hallucinations and improving factua...

Membership Inference Attack with Partial Features

Machine learning models have been shown to be susceptible to membership inference attack, which can be used to determine whether a given sample appears in the training data. Existing membership inference methods commonly assume that the adversary has full access to the features of the target...

Cascading and Proxy Membership Inference Attacks

A Membership Inference Attack MIA assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or non-adaptive, depending on whether the adversary is allowed...