Self-Evolving Defense: Continual Security Policy Learning for LLM Agents

Large language models LLMs increasingly power agents that access sensitive information, use external tools, and modify software repositories. Although these capabilities offer substantial benefits, they also create security risks such as jailbreaks, prompt injection, and vulnerable code generatio...

A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks

Large language models LLMs remain vulnerable to jailbreak attacks that exploit techniques such as role-playing, obfuscation, code transformation, and multi-step indirection to elicit harmful outputs. As jailbreak strategies keep emerging, defenses have proliferated in an ongoing cat-and-mouse gam...

DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction

Large Language Model LLM agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how...

Stateful Cooperative Agents Safeguarding LLMs against Evolving Multi-Turn Attacks

As LLMs become increasingly integrated into complex applications, their vulnerability to adversarial attacks has raised significant concerns. However, existing defenses remain reactive in nature. This limitation makes it difficult for them to counter sophisticated threats, as adversaries...

Malicious code in @self-evolving-harness/kivo (npm)

Source: amazon-inspector ce31b5c287727dabb5479a114843b06b80bbd75db10d74014a00db80b9b321bd The package's LLM pipeline Kivo.ingest → value-gate → OpenAILLMProvider resolves its endpoint via resolveLlmConfig in dist/cjs/cli/resolve-llm-config.js, which hardcodes DEFAULTBASEURL =...

Mako: A Self-Evolving Agentic Operating System (SE-AOS) for Autonomous Web Exploitation

We introduce the Self-Evolving Agentic Operating System SE-AOS: a new class of AI agent that treats exploit capability as a mutable, versioned kernel it extends at runtime, observing its own failures, synthesising new capabilities, proving them against a live target, and hot-loading them back int...

The Gentlemen are knocking: сustom backdoors and evolving tactics

Introduction This year saw the emergence of The Gentlemen, a prominent example of a group operating under the ransomware-as-a-service RaaS model. Although our initial assessment suggested the group first appeared in mid-2025, it actually started ramping up its activities at the beginning of 2026...

PixJail: Self-Evolving Paper-To-Pipeline Reproduction for Text-To-Image Jailbreak Evaluation

As Text-to-Image T2I jailbreak techniques evolve rapidly, existing benchmarks and reproduction workflows often struggle to keep pace. More importantly, T2I jailbreak evaluation is not a single prompt-level test, but a pipeline-level problem shaped by multiple stages, including prompt...

Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security

Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide. A skill may look benign in its documentation or code while becoming harmful only when it is invoked with particular user requests, local assets,...

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifiers cannot adapt to these evolving attacks, while adaptive memory-based guardrails tend to over-refuse benign queries that resemble stored attacks...

Malicious code in @self-evolving-harness/kivo (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector ce31b5c287727dabb5479a114843b06b80bbd75db10d74014a00db80b9b321bd The package's LLM pipeline Kivo.ingest → value-gate → OpenAILLMProvider resolves its endpoint via resolveLlmConfig in...

Bringing Security Visibility to Vercel with Wiz

Giving developers and security teams a shared view of application risk as it evolves...

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs against Evolving Multi-Round Attacks

As Large Language Models LLMs are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety concerns, especially those evolving over multi-round interactions. Existing defenses are largely reactive and struggle to adapt as adversaries refine...

ACORN-IDS: Adaptive Continual Novelty Detection for Intrusion Detection Systems

Intrusion Detection Systems IDS must maintain reliable detection performance under rapidly evolving benign traffic patterns and the continual emergence of cyberattacks, including zero-day threats with no labeled data available. However, most machine learning-based IDS approaches either assume...

Why API Security Is No Longer an AppSec Problem – And What Security Leaders Must Do Instead

APIs are one of the most important technologies in digital business ecosystems. And yet, the responsibility for their security often falls to AppSec teams – and that’s a problem. This organizational mismatch creates systemic risk: business teams assume APIs are “secured,” while attackers exploit...

Why Asia’s Public Sector Is Rethinking Cyber Resilience

...

SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes critical vulnerabilities to prompt injection attacks where...

RunawayEvil: Jailbreaking the Image-To-Video Generative Models

Image-to-Video I2V generation synthesizes dynamic visual content from image and text inputs, providing significant creative control. However, the security of such multimodal systems, particularly their vulnerability to jailbreak attacks, remains critically underexplored. To bridge this gap, we...

New IDC research highlights a major cloud security shift

Cloud security is at a tipping point. While moving to the cloud powers both growth and speed for organizations, it can also bring new risks. According to IDC’s latest research, organizations experienced an average of nine cloud security incidents in 2024, with 89% reporting a year-over-year...

EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense

Modern email spam and phishing attacks have evolved far beyond keyword blacklists or simple heuristics. Adversaries now craft multi-modal campaigns that combine natural-language text with obfuscated URLs, forged headers, and malicious attachments, adapting their strategies within days to bypass...