Evaluating Apple Intelligence'S Writing Tools for Privacy against Large Language Model-Based Inference Attacks: Insights from Early Datasets

The misuse of Large Language Models LLMs to infer emotions from text for malicious purposes, known as emotion inference attacks, poses a significant threat to user privacy. In this paper, we investigate the potential of Apple Intelligence's writing tools, integrated across iPhone, iPad, and...

Clustering and Median Aggregation Improve Differentially Private Inference

Differentially private DP language model inference is an approach for generating private synthetic text. A sensitive input example is used to prompt an off-the-shelf large language model LLM to produce a similar example. Multiple examples can be aggregated together to formally satisfy the DP...

Watermarking Degrades Alignment in Language Models: Analysis and Mitigation

Watermarking techniques for large language models LLMs can significantly impact output quality, yet their effects on truthfulness, safety, and helpfulness remain critically underexamined. This paper presents a systematic analysis of how two popular watermarking approaches-Gumbel and KGW-affect...

Keyed Chaotic Dynamics for Privacy-Preserving Neural Inference

Neural network inference typically operates on raw input data, increasing the risk of exposure during preprocessing and inference. Moreover, neural architectures lack efficient built-in mechanisms for directly authenticating input data. This work introduces a novel encryption method for ensuring...

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack

Membership inference attack MIA has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's training set by analyzing the model's output. While traditional...

Denial Of Service (DoS)

vLLM is vulnerable to Denial of Service DoS. The vulnerability is due to improper input validation that accepts unexpected or malformed pattern and type fields in tool-related requests, which can crash the inference worker...

CSVAR: Enhancing Visual Privacy in Federated Learning Via Adaptive Shuffling against Overfitting

Although federated learning preserves training data within local privacy domains, the aggregated model parameters may still reveal private characteristics. This vulnerability stems from clients' limited training data, which predisposes models to overfitting. Such overfitting enables models to...

Unlearning Inversion Attacks for Graph Neural Networks

Graph unlearning methods aim to efficiently remove the impact of sensitive data from trained GNNs without full retraining, assuming that deleted information cannot be recovered. In this work, we challenge this assumption by introducing the graph unlearning inversion attack: given only black-box...

Improper Input Validation

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Improper Input Validation in the pattern and type fields. An attacker can cause a crash of the inference worker by sending inputs containing...

CVE-2025-48942

vLLM is an inference and serving engine for large language models LLMs. In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid jsonschema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex...

CVE-2025-48944

vLLM is an inference and serving engine for large language models LLMs. In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality ...

CVE-2025-48944

vLLM (inference/serving engine) is affected when running versions 0.8.0 up to but excluding 0.9.0 with the /v1/chat/completions OpenAPI endpoint. The root cause is lack of validation for unexpected or malformed inputs in the pattern and type fields when the tools functionality is invoked, allowin...

CVE-2025-48944 vLLM Tool Schema allows DoS via Malformed pattern and type Fields

vLLM is an inference and serving engine for large language models LLMs. In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality ...

GNU Screen Information Disclosure Vulnerability

GNU Screen is an application from the American GNU community. It provides the effect of getting multiple virtual terminals on one physical terminal. GNU Screen suffers from an information disclosure vulnerability that can be exploited by attackers to infer path information...

vLLM 输入验证错误漏洞

vLLM is a high throughput and memory efficient inference and service engine for LLM from the vLLM open source. An input validation error vulnerability exists in vLLM versions prior to 0.8.0 through 0.9.0, which stems from accidental or malformed inputs in the pattern and type fields that are not...

Chances and Challenges of the Model Context Protocol in Digital Forensics and Incident Response

Large language models hold considerable promise for supporting forensic investigations, but their widespread adoption is hindered by a lack of transparency, explainability, and reproducibility. This paper explores how the emerging Model Context Protocol can address these challenges and support th...

PYSEC-2025-53

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

Bayesian Perspective on Memorization and Reconstruction

We introduce a new Bayesian perspective on the concept of data reconstruction, and leverage this viewpoint to propose a new security definition that, in certain settings, provably prevents reconstruction attacks. We use our paradigm to shed new light on one of the most notorious attacks in the...

Practical Bayes-Optimal Membership Inference Attacks

We develop practical and theoretically grounded membership inference attacks MIAs against both independent and identically distributed i.i.d. data and graph-structured data. Building on the Bayesian decision-theoretic framework of Sablayrolles et al., we derive the Bayes-optimal membership...

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution can exploit these mechanisms to discriminate or unjustly deny services under...