Lucene search
+L

1541 matches found

Packet Storm News
Packet Storm News
added 2025/11/04 12:0 a.m.10 views

Designing Proportionate Cybersecurity Frameworks for European Micro-Enterprises: Lessons from the Squad 2025 Case

Micro and small enterprises SMEs account for most European businesses yet remain highly vulnerable to cyber threats. This paper analyses the design logic of a recent European policy initiative -- the Squad 2025 Playbook on Cybersecurity Awareness for Micro-SMEs -- to extract general principles fo...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/11/03 12:0 a.m.17 views

Scam Shield: Multi-Model Voting and Fine-Tuned LLMs against Adversarial Attacks

Scam detection remains a critical challenge in cybersecurity as adversaries craft messages that evade automated filters. We propose a Hierarchical Scam Detection System HSDS that combines a lightweight multi-model voting front end with a fine-tuned LLaMA 3.1 8B Instruct back end to improve accura...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/31 12:0 a.m.10 views

Sustaining Cyber Awareness: The Long-Term Impact of Continuous Phishing Training and Emotional Triggers

Phishing constitutes more than 90% of successful cyberattacks globally, remaining one of the most persistent threats to organizational security. Despite organizations tripling their cybersecurity budgets between 2015 and 2025, the human factor continues to pose a critical vulnerability. This stud...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/29 12:0 a.m.38 views

AgentCyTE: Leveraging Agentic AI to Generate Cybersecurity Training and Experimentation Scenarios

Designing realistic and adaptive networked threat scenarios remains a core challenge in cybersecurity research and training, still requiring substantial manual effort. While large language models LLMs show promise for automated synthesis, unconstrained generation often yields configurations that...

7.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/25 12:0 a.m.10 views

SecureLearn - an Attack-Agnostic Defense for Multiclass Machine Learning against Data Poisoning Attacks

Data poisoning attacks are a potential threat to machine learning ML models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning attacks or are aligned with particular ML algorithms. Furthermore, most defenses a...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/24 12:0 a.m.8 views

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses

Multimodal large language models MLLMs comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to induce unauthorized or harmful responses. The incorporation o...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/24 12:0 a.m.46 views

Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models

Large language models LLMs remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker mode...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/23 12:0 a.m.12 views

Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses

With the wide application of deep reinforcement learning DRL techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable environments has become a core issue in current research...

6.9AI score
SaveExploits0
hivepro
hivepro
added 2025/10/21 8:7 p.m.7 views

Antivirus Software Outage: Is Your Defense Ready?

Your antivirus software is the trusted gatekeeper of your digital world, silently working in the background to block threats. But what happens when that gatekeeper suddenly walks off the job? A widespread antivirus software outage recently showed us the answer, grinding critical industries to a...

7.2AI score
SaveExploits0
Malwarebytes
Malwarebytes
added 2025/10/21 10:33 a.m.7 views

You can poison AI with just 250 dodgy documents

Researchers have shown how you can corrupt an AI and make it talk gibberish by tampering with just 250 documents. The attack, which involves poisoning the data that an AI trains on, is the latest in a long line of research that has uncovered vulnerabilities in AI models. Anthropic which produces...

7.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/16 12:0 a.m.8 views

PoTS: Proof-Of-Training-Steps for Backdoor Detection in Large Language Models

As Large Language Models LLMs gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are particularly insidious and difficult to detect. Existing...

7.4AI score
SaveExploits0
Microsoft Secure
Microsoft Secure
added 2025/10/13 4:0 p.m.7 views

Building a lasting security culture at Microsoft

At Microsoft, building a lasting security culture is more than a strategic priority—it is a call to action. Security begins and ends with people, which is why every employee plays a critical role in protecting both Microsoft and our customers. When secure practices are woven into how we think,...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/10 12:0 a.m.26 views

Exploiting Web Search Tools of AI Agents for Data Exfiltration

Large language models LLMs are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation RAG allows LLMs to process and retrieve sensitive corporate data, amplifyi...

7.2AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/09 12:0 a.m.6 views

Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models

Large language models LLMs remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints gradually. These attacks target different harm categories like malware generation, harassment, or fraud through distinct conversational approaches...

7.4AI score
SaveExploits0
HackRead
HackRead
added 2025/10/07 2:0 p.m.7 views

INE Security Releases Industry Benchmark Report: “Wired Together: The Case for Cross-Training in Networking and Cybersecurity”

Raleigh, United States, 7th October 2025, CyberNewsWire...

7AI score
SaveExploits0
EUVD
EUVD
added 2025/10/07 12:30 a.m.4 views

EUVD-2013-6511

Malware in sbrugna...

5CVSS6.4AI score0.01703EPSS
SaveExploits1References4
EUVD
EUVD
added 2025/10/07 12:30 a.m.7 views

EUVD-2020-30796

Malware in sbrugna...

6.1CVSS6.4AI score0.00268EPSS
SaveExploits1References2
EUVD
EUVD
added 2025/10/07 12:30 a.m.8 views

EUVD-2013-6770

Malware in sbrugna...

4.3CVSS6.4AI score0.01822EPSS
SaveExploits0References5
EUVD
EUVD
added 2025/10/07 12:30 a.m.4 views

EUVD-2020-24813

Malware in sbrugna...

5.3CVSS5.6AI score0.01079EPSS
SaveExploits0References2
EUVD
EUVD
added 2025/10/07 12:30 a.m.7 views

EUVD-2020-2963

Malware in sbrugna...

8.1CVSS6.6AI score0.01058EPSS
SaveExploits0References3
Rows per page
Query Builder