Lucene search
+L

1659 matches found

Microsoft Secure
Microsoft Secure
added 2026/02/09 5:12 p.m.18 views

A one-prompt attack that breaks LLM safety alignment

Large language models LLMs and diffusion models now power a wide range of applications, from document assistance to text-to-image generation, and users increasingly expect these systems to be safety-aligned by default. Yet safety alignment is only as robust as its weakest failure mode. Despite...

5.7AI score
SaveExploits0
Microsoft Secure
Microsoft Secure
added 2026/02/09 5:12 p.m.21 views

A one-prompt attack that breaks LLM safety alignment

Large language models LLMs and diffusion models now power a wide range of applications, from document assistance to text-to-image generation, and users increasingly expect these systems to be safety-aligned by default. Yet safety alignment is only as robust as its weakest failure mode. Despite...

5.7AI score
SaveExploits0
Veracode
Veracode
added 2026/02/09 12:54 p.m.13 views

Sensitive Information Disclosure

Amazon SageMaker Python SDK is vulnerable to sensitive information disclosure. The vulnerability is due to the ModelBuilder HMAC signing key being returned in cleartext in the DescribeTrainingJob API response, which allows an attacker with API access and S3 output write permissions to upload...

8.5CVSS5.5AI score0.00473EPSS
SaveExploits0References7Affected Software1
Packet Storm News
Packet Storm News
added 2026/02/09 12:00 a.m.15 views

SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity

Deep Reinforcement Learning DRL has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulations to bespoke cyber environments can introduce numerous issues. This is furthe...

5.6AI score
SaveExploits0
GithubExploit
GithubExploit
added 2026/02/06 5:13 a.m.201 views

Exploit for CVE-2025-66478

Vulnerable Mall Next.js Red/Blue Team Training Target Vul...

7AI score
SaveExploits112
Packet Storm News
Packet Storm News
added 2026/02/06 12:00 a.m.18 views

Next-Generation Cyberattack Detection with Large Language Models: Anomaly Analysis across Heterogeneous Logs

This project explores large language models LLMs for anomaly detection across heterogeneous log sources. Traditional intrusion detection systems suffer from high false positive rates, semantic blindness, and data scarcity, as logs are inherently sensitive, making clean datasets rare. We address...

5.5AI score
SaveExploits0
RedhatCVE
RedhatCVE
added 2026/02/03 9:19 p.m.14 views

CVE-2026-1777

The Amazon SageMaker Python SDK before v3.2.0 and v2.256.0 includes the ModelBuilder HMAC signing key in the cleartext response elements of the DescribeTrainingJob function. A third party with permissions to both call this API and permissions to modify objects in the Training Jobs S3 output...

8.5CVSS5.6AI score0.00473EPSS
SaveExploits0References1
CNNVD
CNNVD
added 2026/02/03 12:00 a.m.15 views

NVIDIA Megatron-LM 代码注入漏洞

NVIDIA Megatron-LM is a distributed training framework based on PyTorch developed by NVIDIA Corporation in the United States. It is specifically designed for training large-scale Transformer language models. NVIDIA Megatron-LM has a code injection vulnerability. This vulnerability stems from...

7.8CVSS7.2AI score0.00266EPSS
SaveExploits0References2
Github Security Blog
Github Security Blog
added 2026/02/02 11:33 p.m.26 views

SageMaker Python SDK has Exposed HMAC

Summary SageMaker Python SDK is an open source library for training and deploying machine learning models on Amazon SageMaker. An issue where the HMAC secret key is stored in environment variables and disclosed via the DescribeTrainingJob API has been identified. Impact - Function and Payload...

8.5CVSS6.5AI score0.00473EPSS
SaveExploits0References8Affected Software1
OSV
OSV
added 2026/02/02 11:33 p.m.16 views

GHSA-RJRP-M2JW-PV9C SageMaker Python SDK has Exposed HMAC

Summary SageMaker Python SDK is an open source library for training and deploying machine learning models on Amazon SageMaker. An issue where the HMAC secret key is stored in environment variables and disclosed via the DescribeTrainingJob API has been identified. Impact - Function and Payload...

8.7CVSS6.5AI score0.00473EPSS
SaveExploits0References8
NVD
NVD
added 2026/02/02 11:16 p.m.18 views

CVE-2026-1777

The Amazon SageMaker Python SDK before v3.2.0 and v2.256.0 includes the ModelBuilder HMAC signing key in the cleartext response elements of the DescribeTrainingJob function. A third party with permissions to both call this API and permissions to modify objects in the Training Jobs S3 output...

8.5CVSS0.00473EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
added 2026/02/02 8:10 p.m.6 views

CVE-2026-1777 Cleartext transmission of sensitive materials in aws/sagemaker-python-sdk

The Amazon SageMaker Python SDK before v3.2.0 and v2.256.0 includes the ModelBuilder HMAC signing key in the cleartext response elements of the DescribeTrainingJob function. A third party with permissions to both call this API and permissions to modify objects in the Training Jobs S3 output...

8.5CVSS5.6AI score0.00473EPSS
SaveExploits0References4
ATTACKERKB
ATTACKERKB
added 2026/02/02 8:10 p.m.11 views

CVE-2026-1777

The Amazon SageMaker Python SDK before v3.2.0 and v2.256.0 includes the ModelBuilder HMAC signing key in the cleartext response elements of the DescribeTrainingJob function. A third party with permissions to both call this API and permissions to modify objects in the Training Jobs S3 output...

8.5CVSS5.6AI score0.00473EPSS
SaveExploits0References2
CVE
CVE
added 2026/02/02 8:10 p.m.51 views

CVE-2026-1777

The CVE-2026-1777 issue affects the Amazon SageMaker Python SDK prior to v3.2.0 and v2.256.0, where the ModelBuilder HMAC signing key is exposed in cleartext within DescribeTrainingJob responses. A privileged attacker who can both call DescribeTrainingJob and modify objects in the Training Jobs S...

8.5CVSS5.6AI score0.00473EPSS
SaveExploits0References4
Cvelist
Cvelist
added 2026/02/02 8:10 p.m.35 views

CVE-2026-1777 Cleartext transmission of sensitive materials in aws/sagemaker-python-sdk

The Amazon SageMaker Python SDK before v3.2.0 and v2.256.0 includes the ModelBuilder HMAC signing key in the cleartext response elements of the DescribeTrainingJob function. A third party with permissions to both call this API and permissions to modify objects in the Training Jobs S3 output...

8.5CVSS0.00473EPSS
SaveExploits0References4
Positive Technologies
Positive Technologies
added 2026/02/02 12:00 a.m.36 views

PT-2026-6479

Summary SageMaker Python SDK is an open source library for training and deploying machine learning models on Amazon SageMaker. An issue where the HMAC secret key is stored in environment variables and disclosed via the DescribeTrainingJob API has been identified. Impact - Function and Payload...

8.5CVSS6.4AI score0.00473EPSS
SaveExploits0References9
GithubExploit
GithubExploit
added 2026/02/01 9:43 a.m.307 views

Exploit for CVE-2023-39848

DAMN VULNERABLE WEB APPLICATION Damn Vulnerable Web Applicati...

5.8AI score
SaveExploits4
Packet Storm News
Packet Storm News
added 2026/01/30 12:00 a.m.11 views

AEGIS: White-Box Attack Path Generation Using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises

Creating attack paths for cyber defence exercises requires substantial expert effort. Existing automation requires vulnerability graphs or exploit sets curated in advance, limiting where it can be applied. We present AEGIS, a system that generates attack paths using LLMs, white-box access, and...

5.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/01/28 12:00 a.m.19 views

ShellForge: Adversarial Co-Evolution of Webshell Generation and Multi-View Detection for Robust Webshell Defense

Webshells remain a primary foothold for attackers to compromise servers, particularly within PHP ecosystems. However, existing detection mechanisms often struggle to keep pace with rapid variant evolution and sophisticated obfuscation techniques that camouflage malicious intent. Furthermore, many...

5.5AI score
SaveExploits0
NVD
NVD
added 2026/01/22 5:16 p.m.14 views

CVE-2026-1260

Invalid memory access in Sentencepiece versions less than 0.2.1 when using a vulnerable model file, which is not created in the normal training procedure...

8.5CVSS0.00165EPSS
SaveExploits0References6
Rows per page
Query Builder