Tag: LLM security
Browse our exclusive articles!
VulTriage: Enhanced LLM Vulnerability Detection Framework
Discover VulTriage, a triple-path context augmentation framework improving LLM-based software vulnerability detection with control, knowledge, and semantic...
Agent-BOM: Unified Security Auditing for LLM Agents
Discover Agent-BOM, a novel graph-based framework enhancing security audits for LLM agentic systems by bridging semantic gaps and assessing risks.
MAGE: Protecting LLM Agents from Long-Horizon Threats
Discover how MAGE enhances LLM agent safety by using shadow memory to detect and prevent long-horizon threats with minimal overhead.
PIIGuard: Top Defense Against PII Harvesting Online
Discover how PIIGuard protects webpages from PII harvesting by LLMs using advanced adversarial sanitization techniques.
EvoJail: Adaptive Diverse Jailbreak Prompts for LLMs
Discover EvoJail, an evolutionary framework generating diverse, adaptive jailbreak prompts to enhance safety and robustness in large language models.