915 matches found
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...
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...
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...
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...
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...
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...
EUVD-2025-199390
Malicious code in @voiceflow/semantic-release-config npm...
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...
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...
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...
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...
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...
EUVD-2025-180362
Malicious code in archaeogenetics-semantic-ui-weywot-gravity npm...
EUVD-2025-179990
Malicious code in bootstrap-semantic-release-pulsar-koa npm...
EUVD-2025-177445
Malicious code in ophiuchus-callisto-semantic-ui-lynx npm...
EUVD-2025-178784
Malicious code in gammarayburst-semantic-ui-antares-juno npm...
EUVD-2025-176673
Malicious code in resolvers-semantic-ui-cosmochemistry-andromeda npm...
EUVD-2025-177656
Malicious code in neptune-redshift-semantic-release-xml npm...