Lucene search
+L

1413 matches found

RedHat Linux
RedHat Linux
added 2025/07/07 10:29 a.m.5 views

Moderate: Red Hat Security Advisory: Red Hat AI Inference Server 3.0 (CUDA)

Red Hat AI Inference Server 3.0 CUDA is now available. Red Hat® AI Inference Server...

9.8CVSS7.2AI score0.00948EPSS
SaveExploits1References3
RedHat Linux
RedHat Linux
added 2025/07/07 10:28 a.m.12 views

Moderate: Red Hat Security Advisory: Red Hat AI Inference Server 3.0 (ROCm)

Red Hat AI Inference Server 3.0 ROCm is now available. Red Hat® AI Inference Server...

9.8CVSS7.2AI score0.00948EPSS
SaveExploits1References3
Packet Storm News
Packet Storm News
added 2025/07/07 12:0 a.m.7 views

Cascade: Token-Sharded Private LLM Inference

As LLMs continue to increase in parameter size, the computational resources required to run them are available to fewer parties. Therefore, third-party inference services -- where LLMs are hosted by third parties with significant computational resources -- are becoming increasingly popular...

6.9AI score
SaveExploits0
NVD
NVD
added 2025/07/01 2:15 p.m.26 views

CVE-2025-6920

A flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/ endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows...

5.3CVSS0.00268EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
added 2025/07/01 1:16 p.m.17 views

CVE-2025-6920 Ai-inference-server: authentication bypass via unprotected inference endpoint in api

A flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/ endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows...

5.3CVSS7AI score0.00268EPSS
SaveExploits0References2
Cvelist
Cvelist
added 2025/07/01 1:16 p.m.28 views

CVE-2025-6920 Ai-inference-server: authentication bypass via unprotected inference endpoint in api

A flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/ endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows...

5.3CVSS0.00268EPSS
SaveExploits0References2
CVE
CVE
added 2025/07/01 1:16 p.m.47 views

CVE-2025-6920

CVE-2025-6920 affects ai-inference-server: the POST /invocations endpoint bypasses API key validation, permitting unauthorized access to inference features and potentially backend resources. Affected: model inference API under /v1/*; root cause: authentication enforcement failure on /invocations....

5.3CVSS6.4AI score0.00268EPSS
SaveExploits0References2Affected Software1
Positive Technologies
Positive Technologies
added 2025/07/01 12:0 a.m.11 views

PT-2025-27527 · Unknown · Ai-Inference-Server

Name of the Vulnerable Software and Affected Versions: ai-inference-server affected versions not specified Description: A flaw was found in the authentication enforcement mechanism of a model inference API. The issue affects the "/v1/" endpoints, where API key validation is expected but not...

5.3CVSS6.2AI score0.00268EPSS
SaveExploits0References8
Debian CVE
Debian CVE
added 2025/06/24 3:21 a.m.8 views

CVE-2025-52566

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation llamavocab::tokenize src/llama-vocab.cpp:3036 resulting in unintended behavior in tokens copying size comparison. Allowing...

8.8CVSS5.3AI score0.00318EPSS
SaveExploits1
Packet Storm News
Packet Storm News
added 2025/06/23 12:0 a.m.7 views

Amplifying Machine Learning Attacks through Strategic Compositions

Machine learning ML models are proving to be vulnerable to a variety of attacks that allow the adversary to learn sensitive information, cause mispredictions, and more. While these attacks have been extensively studied, current research predominantly focuses on analyzing each attack type...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/22 12:0 a.m.12 views

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models

Large vision-language models LVLMs have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information. Therefore, it is important to detect whether an image is used t...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/22 12:0 a.m.8 views

SecONNds: Secure Outsourced Neural Network Inference on ImageNet

The widespread adoption of outsourced neural network inference presents significant privacy challenges, as sensitive user data is processed on untrusted remote servers. Secure inference offers a privacy-preserving solution, but existing frameworks suffer from high computational overhead and...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/22 12:0 a.m.22 views

HE-LRM: Encrypted Deep Learning Recommendation Models Using Fully Homomorphic Encryption

Fully Homomorphic Encryption FHE is an encryption scheme that not only encrypts data but also allows for computations to be applied directly on the encrypted data. While computationally expensive, FHE can enable privacy-preserving neural inference in the client-server setting: a client encrypts...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/22 12:0 a.m.11 views

UCD: Unlearning in LLMs Via Contrastive Decoding

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models LLMs while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive decoding, leveraging two auxiliary smaller models, one train...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/22 12:0 a.m.10 views

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: a New Inference Attack Perspective

Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning ensures complete data removal equivalent to retraining, it is impractical for large-scale models, leading to growing...

7.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/21 12:0 a.m.8 views

Don't Throw the Baby out with the Bathwater: How and Why Deep Learning for ARC

The Abstraction and Reasoning Corpus ARC-AGI presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for generating skillful state-of-the-art neural networks NN across varied modalities and...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/21 12:0 a.m.8 views

Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference

Differential privacy DP auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many training runs that are prohibitively costly, recent work introduces one-run auditing approaches that effectively audit DP-SGD...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/21 12:0 a.m.7 views

ReDASH: Fast and efficient Scaling in Arithmetic Garbled Circuits for Secure Outsourced Inference

Whitepaper called ReDASH: Fast and efficient Scaling in Arithmetic Garbled Circuits for Secure Outsourced Inference...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/19 12:0 a.m.10 views

Black-Box Privacy Attacks on Shared Representations in Multitask Learning

Multitask learning MTL has emerged as a powerful paradigm that leverages similarities among multiple learning tasks, each with insufficient samples to train a standalone model, to solve them simultaneously while minimizing data sharing across users and organizations. MTL typically accomplishes th...

6.6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/12 12:0 a.m.5 views

SOFT: Selective Data Obfuscation for Protecting LLM Fine-Tuning against Membership Inference Attacks

Whitepaper called SOFT: Selective Data Obfuscation For Protecting LLM Fine-Tuning Against Membership Inference Attacks...

7AI score
SaveExploits0
Rows per page
Query Builder