Lucene search
+L

205 matches found

Positive Technologies
Positive Technologies
•added 2025/06/24 12:00 a.m.•10 views

PT-2025-26690

Name of the Vulnerable Software and Affected Versions: llama.cpp version prior to b5721 Description: The issue is related to a signed vs. unsigned integer overflow in the llama vocab::tokenize function of llama.cpp's tokenizer implementation, resulting in unintended behavior during token copying...

8.8CVSS6.5AI score0.00363EPSS
SaveExploits1References22
Amazon
Amazon
•added 2025/06/23 12:00 a.m.•15 views

Medium: amazon-cloudwatch-agent

Issue Overview: The tokenizer incorrectly interprets tags with unquoted attribute values that end with a solidus character / as self-closing. When directly using Tokenizer, this can result in such tags incorrectly being marked as self-closing, and when using the Parse functions, this can result i...

7.5CVSS9.8AI score0.00666EPSS
SaveExploits0
The Hacker News
The Hacker News
•added 2025/06/12 1:52 p.m.•22 views

New TokenBreak Attack Bypasses AI Moderation with Single-Character Text Changes

Cybersecurity researchers have discovered a novel attack technique called TokenBreak that can be used to bypass a large language model's LLM safety and content moderation guardrails with just a single character change. "The TokenBreak attack targets a text classification model's tokenization...

7.6AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2025/06/12 1:52 p.m.•14 views

New TokenBreak Attack Bypasses AI Moderation with Single-Character Text Changes

Cybersecurity researchers have discovered a novel attack technique called TokenBreak that can be used to bypass a large language model's LLM safety and content moderation guardrails with just a single character change. "The TokenBreak attack targets a text classification model's tokenization...

5.6AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2025/06/06 12:00 a.m.•55 views

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation RAG systems enhance Large Language Models LLMs by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on...

7.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2025/05/26 12:00 a.m.•19 views

Language of Network: a Generative Pre-Trained Model for Encrypted Traffic Comprehension

The increasing demand for privacy protection and security considerations leads to a significant rise in the proportion of encrypted network traffic. Since traffic content becomes unrecognizable after encryption, accurate analysis is challenging, making it difficult to classify applications and...

6.6AI score
SaveExploits0
RedhatCVE
RedhatCVE
•added 2025/05/22 9:36 p.m.•15 views

CVE-2021-43854

NLTK Natural Language Toolkit is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. Versions prior to 3.6.5 are vulnerable to regular expression denial of service ReDoS attacks. The vulnerability is present in...

7.5CVSS6.7AI score0.0279EPSS
SaveExploits1
Positive Technologies
Positive Technologies
•added 2025/04/29 12:00 a.m.•24 views

PT-2025-18141

Name of the Vulnerable Software and Affected Versions huggingface/transformers library version v4.48.1 Description A Regular Expression Denial of Service ReDoS vulnerability was identified in the huggingface/transformers library, specifically in the file tokenization gpt neox japanese.py of the...

6.5CVSS6.2AI score0.00484EPSS
SaveExploits1References16
Packet Storm News
Packet Storm News
•added 2025/04/18 12:00 a.m.•36 views

Detecting Zero-Day Web Attacks with an Ensemble of LSTM, GRU, and Stacked Autoencoders

The rapid growth in web-based services has significantly increased security risks related to user information, as web-based attacks become increasingly sophisticated and prevalent. Traditional security methods frequently struggle to detect previously unknown zero-day web attacks, putting sensitiv...

6.7AI score
SaveExploits0
osv_azl
osv_azl
•added 2025/04/16 6:16 p.m.•18 views

AZL-60485 CVE-2025-22872 affecting package telegraf for versions less than 1.31.0-10

The tokenizer incorrectly interprets tags with unquoted attribute values that end with a solidus character / as self-closing. When directly using Tokenizer, this can result in such tags incorrectly being marked as self-closing, and when using the Parse functions, this can result in content...

6.5CVSS6.6AI score0.00545EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
•added 2025/03/22 1:11 p.m.•21 views

CVE-2024-12720

A Regular Expression Denial of Service ReDoS vulnerability was identified in the huggingface/transformers library, specifically in the file tokenizationnougatfast.py. The vulnerability occurs in the postprocesssingle function, where a regular expression processes specially crafted input. The issu...

7.5CVSS6.7AI score0.00747EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
•added 2025/03/20 10:11 a.m.•18 views

CVE-2024-12720 Regular Expression Denial of Service (ReDoS) in huggingface/transformers

A Regular Expression Denial of Service ReDoS vulnerability was identified in the huggingface/transformers library, specifically in the file tokenizationnougatfast.py. The vulnerability occurs in the postprocesssingle function, where a regular expression processes specially crafted input. The issu...

5.3CVSS5.2AI score0.00747EPSS
SaveExploits0References2
osv_cve
osv_cve
•added 2025/03/20 10:11 a.m.•22 views

CVE-2024-12720 Regular Expression Denial of Service (ReDoS) in huggingface/transformers

A Regular Expression Denial of Service ReDoS vulnerability was identified in the huggingface/transformers library, specifically in the file tokenizationnougatfast.py. The vulnerability occurs in the postprocesssingle function, where a regular expression processes specially crafted input. The issu...

5.3CVSS6.4AI score0.00747EPSS
SaveExploits0References4
OSSF Malicious Packages
OSSF Malicious Packages
•added 2025/02/03 8:16 a.m.•11 views

Malicious code in climate-tokenization-engine-ui (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware c6c54fe1dfe0ee0595094f7b5480bc0761286fb1ad1460e48b4eb6be7e274f52 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

6.9AI score
SaveExploits0References1
osv_mal
osv_mal
•added 2025/02/03 8:16 a.m.•10 views

MAL-2025-1074 Malicious code in climate-tokenization-engine-ui (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware c6c54fe1dfe0ee0595094f7b5480bc0761286fb1ad1460e48b4eb6be7e274f52 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

7AI score
SaveExploits0References1
OSSF Malicious Packages
OSSF Malicious Packages
•added 2025/01/30 4:55 p.m.•13 views

Malicious code in tokenization-lab (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=-...

6.9AI score
SaveExploits0
osv_mal
osv_mal
•added 2025/01/30 4:55 p.m.•12 views

MAL-2025-692 Malicious code in tokenization-lab (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=-...

7.1AI score
SaveExploits0
HackRead
HackRead
•added 2024/05/29 12:01 p.m.•29 views

Blocksquare Hits $100M Tokenized RWA Triggering Launchpad Release

By Uzair Amir Blocksquare, a leading real estate tokenization platform, announces a major milestone: $100 million worth of real estate tokenized… This is a post from HackRead.com Read the original post: Blocksquare Hits $100M Tokenized RWA Triggering Launchpad Release...

7.3AI score
SaveExploits0
HackRead
HackRead
•added 2024/05/29 12:01 p.m.•26 views

Blocksquare Hits $100M Tokenized RWA Triggering Launchpad Release

By Uzair Amir Blocksquare, a leading real estate tokenization platform, announces a major milestone: $100 million worth of real estate tokenized… This is a post from HackRead.com Read the original post: Blocksquare Hits $100M Tokenized RWA Triggering Launchpad Release...

7.3AI score
SaveExploits0
osv_bit
osv_bit
•added 2024/03/06 11:10 a.m.•73 views

BIT-VAULT-2022-25244

Vault Enterprise clusters using the tokenization transform feature can expose the tokenization key through the tokenization key configuration endpoint to authorized operators with read permissions on this endpoint. Fixed in Vault Enterprise 1.9.4, 1.8.9 and 1.7.10...

6.5CVSS6.3AI score0.00953EPSS
SaveExploits0References3
Rows per page
Query Builder