Lucene search
+L

915 matches found

Packet Storm News
Packet Storm News
added 2025/12/21 12:00 a.m.16 views

Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model LLM-based systems. We present an efficient and systematically evaluated defense architecture that mitigates these threats through a lightweight, multi-stage pipeline. Its core component is a...

7.2AI score
SaveExploits0
CVE
CVE
added 2025/12/16 12:53 a.m.25 views

CVE-2025-68113

CVE-2025-68113 (ALTCHA) describes a cryptographic semantic binding flaw in ALTCHA libraries where the HMAC does not unambiguously bind challenge parameters to the nonce, enabling potential replay of previously solved challenges depending on server-side handling. Affected components include ALTCHA...

6.5CVSS6.3AI score0.00452EPSS
SaveExploits0References10
Github Security Blog
Github Security Blog
added 2025/12/16 12:43 a.m.15 views

ALTCHA Proof-of-Work Vulnerable to Challenge Splicing and Replay

Impact A cryptographic semantic binding flaw in ALTCHA libraries allows challenge payload splicing, which may enable replay attacks. The HMAC signature does not unambiguously bind challenge parameters to the nonce, allowing an attacker to reinterpret a valid proof-of-work submission with a modifi...

6.5CVSS6.7AI score0.00452EPSS
SaveExploits0References13Affected Software5
Packet Storm News
Packet Storm News
added 2025/12/16 12:00 a.m.14 views

SeBERTis: A Framework for Producing Classifiers of Security-Related Issue Reports

Monitoring issue tracker submissions is a crucial software maintenance activity. A key goal is the prioritization of high risk, security-related bugs. If such bugs can be recognized early, the risk of propagation to dependent products and endangerment of stakeholder benefits can be mitigated. To...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/12/14 12:00 a.m.11 views

CeLLMate: Sandboxing Browser AI Agents

Browser-using agents BUAs are an emerging class of autonomous agents that interact with web browsers in human-like ways, including clicking, scrolling, filling forms, and navigating across pages. While these agents help automate repetitive online tasks, they are vulnerable to prompt injection...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/12/04 12:00 a.m.14 views

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models

Large Language Models LLMs have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal domains. Most existing jailbreak methods revolve around Prompt...

6.9AI score
SaveExploits0
EUVD
EUVD
added 2025/11/25 12:16 a.m.9 views

EUVD-2025-199390

Malicious code in @voiceflow/semantic-release-config npm...

6.6AI score
SaveExploits0References3
OSSF Malicious Packages
OSSF Malicious Packages
added 2025/11/25 12:16 a.m.13 views

Malicious code in @voiceflow/semantic-release-config (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 95a6c9bc458bfc9330434e338d86e85de8f5e6f5a2374749939e909a392268ad The package @voiceflow/semantic-release-config was found to contain malicious code. Source: ghsa-malware...

6.9AI score
SaveExploits0References4
Snyk
Snyk
added 2025/11/24 4:24 p.m.3 views

Embedded Malicious Code

Overview Affected versions of this package are vulnerable to Embedded Malicious Code. This package contains malicious code associated with the Sha1-hulud supply chain attack, and its content was removed from the official package manager. The malware functions as a self-replicating worm capable of...

9.8CVSS6.8AI score
SaveExploits0References3
Packet Storm News
Packet Storm News
added 2025/11/18 12:00 a.m.27 views

From Topology to Behavioral Semantics: Enhancing BGP Security by Understanding BGP's Language with LLMs

The trust-based nature of Border Gateway Protocol BGP makes it vulnerable to disruptions like prefix hijacking and misconfigurations, threatening routing stability. Traditional detection relies on manual inspection with limited scalability. Machine/Deep Learning M/DL approaches automate detection...

6.4AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/11/18 12:00 a.m.29 views

Steganographic Backdoor Attacks in NLP: Ultra-Low Poisoning and Defense Evasion

Transformer models are foundational to natural language processing NLP applications, yet remain vulnerable to backdoor attacks introduced through poisoned data, which implant hidden behaviors during training. To strengthen the ability to prevent such compromises, recent research has focused on...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/11/14 12:00 a.m.12 views

NegBLEURT Forest: Leveraging Inconsistencies for Detecting Jailbreak Attacks

Jailbreak attacks designed to bypass safety mechanisms pose a serious threat by prompting LLMs to generate harmful or inappropriate content, despite alignment with ethical guidelines. Crafting universal filtering rules remains difficult due to their inherent dependence on specific contexts. To...

7.2AI score
SaveExploits0
EUVD
EUVD
added 2025/11/13 3:23 a.m.6 views

EUVD-2025-180362

Malicious code in archaeogenetics-semantic-ui-weywot-gravity npm...

6.6AI score
SaveExploits0
EUVD
EUVD
added 2025/11/13 3:23 a.m.3 views

EUVD-2025-179990

Malicious code in bootstrap-semantic-release-pulsar-koa npm...

6.6AI score
SaveExploits0
EUVD
EUVD
added 2025/11/13 3:23 a.m.6 views

EUVD-2025-177445

Malicious code in ophiuchus-callisto-semantic-ui-lynx npm...

6.6AI score
SaveExploits0
EUVD
EUVD
added 2025/11/13 3:23 a.m.9 views

EUVD-2025-178784

Malicious code in gammarayburst-semantic-ui-antares-juno npm...

6.6AI score
SaveExploits0
EUVD
EUVD
added 2025/11/13 3:23 a.m.8 views

EUVD-2025-176673

Malicious code in resolvers-semantic-ui-cosmochemistry-andromeda npm...

6.6AI score
SaveExploits0
EUVD
EUVD
added 2025/11/13 3:23 a.m.5 views

EUVD-2025-177656

Malicious code in neptune-redshift-semantic-release-xml npm...

6.6AI score
SaveExploits0
EUVD
EUVD
added 2025/11/13 3:23 a.m.9 views

EUVD-2025-176435

Malicious code in semantic-release-webdriver-mocha-holography-init npm...

6.6AI score
SaveExploits0
EUVD
EUVD
added 2025/11/13 3:23 a.m.7 views

EUVD-2025-180326

Malicious code in ariel-semantic-release-optimize-css-assets-webpack-plugin-prettier-plugin-markdown npm...

6.6AI score
SaveExploits0
Rows per page
Query Builder