Lucene search
+L

729 matches found

RedhatCVE
RedhatCVE
added 2026/01/09 8:48 a.m.11 views

CVE-2025-23348

NVIDIA Megatron-LM for all platforms contains a vulnerability in the pretraingpt script, where malicious data created by an attacker may cause a code injection issue. A successful exploit of this vulnerability may lead to code execution, escalation of privileges, information disclosure, and data...

7.8CVSS7.4AI score0.00238EPSS
SaveExploits0References1
Zero Day Initiative
Zero Day Initiative
added 2026/01/09 12:00 a.m.12 views

(0Day) GPT Academic run_in_subprocess_wrapper_func Deserialization of Untrusted Data Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of GPT Academic. Authentication is not required to exploit this vulnerability. The specific flaw exists within the runinsubprocesswrapperfunc function. The issue results from the lack of proper validati...

9.8CVSS7.7AI score0.0114EPSS
SaveExploits0
Positive Technologies
Positive Technologies
added 2026/01/09 12:00 a.m.27 views

PT-2026-1994

Name of the Vulnerable Software and Affected Versions GPT Academic affected versions not specified Description A flaw exists that allows remote attackers to execute arbitrary code on affected installations of GPT Academic. Authentication is not required to exploit this issue. The vulnerability is...

9.8CVSS9.1AI score0.0114EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
added 2026/01/09 12:00 a.m.11 views

PT-2026-1992

Name of the Vulnerable Software and Affected Versions GPT Academic affected versions not specified Description A flaw exists in the stream daas function that allows remote attackers to execute arbitrary code on affected systems. This is due to insufficient validation of user-supplied data, leadin...

8.1CVSS8.5AI score0.00665EPSS
SaveExploits0References2
Zero Day Initiative
Zero Day Initiative
added 2026/01/09 12:00 a.m.11 views

(0Day) GPT Academic stream_daas Deserialization of Untrusted Data Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of GPT Academic. Interaction with a malicious DAAS server is required to exploit this vulnerability but attack vectors may vary depending on the implementation. The specific flaw exists within the...

8.1CVSS7.6AI score0.00665EPSS
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/01/01 12:00 a.m.45 views

Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-Based LLM Systems

Low-Rank Adaptation LoRA has become a popular solution for fine-tuning large language models LLMs in federated settings, dramatically reducing update costs by introducing trainable low-rank matrices. However, when integrated with frameworks like FedIT, LoRA introduces a critical vulnerability:...

7AI score
SaveExploits0
Patchstack
Patchstack
added 2025/12/31 12:00 a.m.14 views

WordPress AI Power: Complete AI Pack plugin <= 1.8.96 - Authenticated (Admin+) PHP Object Injection via wpaicg_export_prompts vulnerability

Authenticated Admin+ PHP Object Injection via wpaicgexportprompts vulnerability discovered by Tran Anh Duc in WordPress Plugin GPT3 AI Content Writer versions = 1.8.96...

7.2CVSS7.3AI score0.00653EPSS
SaveExploits0References1Affected Software1
Positive Technologies
Positive Technologies
added 2025/12/18 12:00 a.m.8 views

PT-2025-52381

Name of the Vulnerable Software and Affected Versions Hugging Face Transformers megatron gpt2 affected versions not specified Description A flaw exists in the parsing of checkpoints within Hugging Face Transformers megatron gpt2, stemming from insufficient validation of user-supplied data. This c...

7.8CVSS7.6AI score0.00322EPSS
SaveExploits0References4
Packet Storm News
Packet Storm News
added 2025/11/28 12:00 a.m.10 views

Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities

Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models LLMs present promising capabilities for automating this task. However, existing research has primarily assessed LLMs using publicly disclosed vulnerabilities, leaving their...

7.4AI score
SaveExploits0
Patchstack
Patchstack
added 2025/11/25 7:21 a.m.17 views

WordPress AI Engine for WordPress: ChatGPT, GPT Content Generator plugin <= 1.0.1 - Authenticated (Contributor+) Arbitrary File Read vulnerability

Authenticated Contributor+ Arbitrary File Read vulnerability discovered by Ryan Kozak in WordPress Plugin AI Engine for WordPress: ChatGPT, GPT Content Generator versions = 1.0.1...

6.5CVSS7AI score0.00492EPSS
SaveExploits1References1Affected Software1
GithubExploit
GithubExploit
added 2025/11/24 3:56 p.m.178 views

injection-research

injection-research A study comparing injection vulnerabilities...

7.7AI score
SaveExploits0
Tenable Nessus
Tenable Nessus
added 2025/11/20 12:00 a.m.5 views

TencentOS Server 3: gdisk (TSSA-2022:0237)

The version of Tencent Linux installed on the remote TencentOS Server 3 host is prior to tested version. It is, therefore, affected by multiple vulnerabilities as referenced in the TSSA-2022:0237 advisory. Package updates are available for TencentOS Server 3 that fix the following vulnerabilities...

7.2CVSS6.9AI score0.00436EPSS
SaveExploits0References3
HackRead
HackRead
added 2025/11/17 1:20 p.m.8 views

EchoGram Flaw Bypasses Guardrails in Major LLMs

HiddenLayer reveals the EchoGram vulnerability, which bypasses safety guardrails on GPT-5.1 and other major LLMs, giving security teams just a 3-month head start...

7.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/11/06 12:00 a.m.10 views

Trustworthiness Calibration Framework for Phishing Email Detection Using Large Language Models

Phishing emails continue to pose a persistent challenge to online communication, exploiting human trust and evading automated filters through realistic language and adaptive tactics. While large language models LLMs such as GPT-4 and LLaMA-3-8B achieve strong accuracy in text classification, thei...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/11/06 12:00 a.m.12 views

GPT-5 at CTFs: Case Studies from Top-Tier Cybersecurity Events

OpenAI and DeepMind's AIs recently got gold at the IMO math olympiad and ICPC programming competition. We show frontier AI is similarly good at hacking by letting GPT-5 compete in elite CTF cybersecurity competitions. In one of this year's hardest events, it outperformed 93% of humans finishing...

6.9AI score
SaveExploits0
Akamai Blog
Akamai Blog
added 2025/10/10 3:00 p.m.11 views

AI Pulse: OpenAI’s Wild Bot Behavior After GPT-5

The AI Pulse series breaks down traffic trends and what they mean for apps, APIs, and businesses. In this post, read how OpenAI’s bots are changing after GPT-5...

7AI score
SaveExploits0
EUVD
EUVD
added 2025/10/07 12:30 a.m.8 views

EUVD-2017-2709

Malware in sbrugna...

7.8CVSS7.9AI score0.00137EPSS
SaveExploits0References2
EUVD
EUVD
added 2025/10/07 12:30 a.m.11 views

EUVD-2018-3302

Malware in sbrugna...

7.8CVSS7.7AI score0.00202EPSS
SaveExploits0References4
EUVD
EUVD
added 2025/10/07 12:30 a.m.8 views

EUVD-2017-7247

Malware in sbrugna...

7.8CVSS7.7AI score0.00202EPSS
SaveExploits0References4
EUVD
EUVD
added 2025/10/07 12:30 a.m.11 views

EUVD-2015-8746

Malware in sbrugna...

9.3CVSS7.9AI score0.00543EPSS
SaveExploits0References4
Rows per page
Query Builder