Jailbreaking Attacks Vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?

As large language models LLMs are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies reporting high success rates in evading common LLMs. However,...

Large Language Models for Security Operations Centers: a Comprehensive Survey

Large Language Models LLMs have emerged as powerful tools capable of understanding and generating human-like text, offering transformative potential across diverse domains. The Security Operations Center SOC, responsible for safeguarding digital infrastructure, represents one of these domains. SO...

A Kolmogorov-Arnold Network for Interpretable Cyberattack Detection in AGC Systems

Automatic Generation Control AGC is essential for power grid stability but remains vulnerable to stealthy cyberattacks, such as False Data Injection Attacks FDIAs, which can disturb the system's stability while evading traditional detection methods. Unlike previous works that relied on blackbox...

PotentRegion4MalDetect: Advanced Features from Potential Malicious Regions for Malware Detection

Malware developers exploit the fact that most detection models focus on the entire binary to extract the feature rather than on the regions of potential maliciousness. Therefore, they reverse engineer a benign binary and inject malicious code into it. This obfuscation technique circumvents the...

Intelligent ARP Spoofing Detection Using Multi-Layered Machine Learning (ML) Techniques for IoT Networks

Address Resolution Protocol ARP spoofing remains a critical threat to IoT networks, enabling attackers to intercept, modify, or disrupt data transmission by exploiting ARP's lack of authentication. The decentralized and resource-constrained nature of IoT environments amplifies this vulnerability,...

HeavyWater and SimplexWater: Watermarking Low-Entropy Text Distributions

Large language model LLM watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate by changing the next-token predictions output by an LLM. The updated i.e., watermarked predictions depend on random side...

Microsoft Says Fireball Malware Threat 'Overblown'

Check Point has ramped down its projections on the impact of the recently disclosed Fireball malware after Microsoft called its initial numbers into question. Details on Fireball were published June 1 by Check Point, which said the malware was the work of a Chinese digital marketing agency called...