Researchers left AI agents alone in a virtual town and watched it all unravel

Tech leaders have spent the past year telling everyone that AI agents are about to run financial systems, file your tax returns, and quietly buy your groceries. Just leave them alone, the rhetoric goes; they'll handle it. But a New York startup left ten of them alone in a virtual town for two...

BIT-MONGODB-2026-8053 FlatBSON Duplicate Field Index Drift

An issue in MongoDB Server's time-series collection implementation allows an authenticated user with database write privileges to trigger an out-of-bounds memory write in the mongod process. The issue results from an inconsistency in the internal field-name-to-index mapping within the time-series...

Context-Aware Web Attack Detection in Open-Source SIEM Systems Via MITRE ATT&CK-Enriched Behavioral Profiling

Security Information and Event Management SIEM systems aggregate log data from heterogeneous sources to detect coordinated attacks. Traditional rule-based correlation engines struggle to classify multi-step web application attacks because they examine each event without reference to the behaviour...

CVE-2026-8053 FlatBSON Duplicate Field Index Drift

An issue in MongoDB Server's time-series collection implementation allows an authenticated user with database write privileges to trigger an out-of-bounds memory write in the mongod process. The issue results from an inconsistency in the internal field-name-to-index mapping within the time-series...

ClawGuard: Out-Of-Band Detection of LLM Agent Workflow Hijacking Via EM Side Channel

Autonomous LLM agents face a critical security risk known as workflow hijacking, where attackers subtly alter tool and skill invocations. Existing defenses rely on host-internal telemetry such as audit logs, which can be forged if the host OS is compromised. To solve this, we introduce ClawGuard,...

FIRCE: A Framework for Intrusion Response and Conformal Evaluation

Machine learning-based intrusion detection systems deployed in real-world environments frequently suffer from model degradation due to concept drift, where changes in traffic patterns invalidate training assumptions. To address this, we present FIRCE, a Framework for Intrusion Response and...

Trident: Improving Malware Detection with LLMs and Behavioral Features

Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE header contents. One barrier to incorporating dynamic analysis features has been the semi-structured nature of sandbox behavior reports. We show that,...

MARD: A Multi-Agent Framework for Robust Android Malware Detection

With the rapid evolution of Android applications, traditional machine learning-based detection models suffer from concept drift. Additionally, they are constrained by shallow features, lacking deep semantic understanding and interpretability of decisions. Although Large Language Models LLMs...

Detecting Concept Drift in Evolving Malware Families Using Rule-Based Classifier Representations

This work proposes a structural approach to concept drift detection in malware classification using decision tree rulesets. Classifiers are trained across temporal windows on the EMBER2024 dataset, and drift is quantified by comparing extracted rule representations using feature importance,...

IaC Inventory: A Unified View Across Code, Deployments, and Cloud

As AI applications introduce a new class of infrastructure resources, visibility into what your IaC creates, where it runs, and whether it has drifted has never been more critical...

Robust Semi-Supervised Temporal Intrusion Detection for Adversarial Cloud Networks

Cloud networks increasingly rely on machine learning based Network Intrusion Detection Systems to defend against evolving cyber threats. However, real-world deployments are challenged by limited labeled data, non-stationary traffic, and adaptive adversaries. While semi-supervised learning can...

CVE-2026-35618 OpenClaw < 2026.3.23 - Replay Identity Drift via Query-Only Variants in Plivo V2 Verification

OpenClaw before 2026.3.23 contains a replay identity vulnerability in Plivo V2 signature verification that allows attackers to bypass replay protection by modifying query parameters. The verification path derives replay keys from the full URL including query strings instead of the canonicalized...

CVE-2026-35618 OpenClaw < 2026.3.23 - Replay Identity Drift via Query-Only Variants in Plivo V2 Verification

OpenClaw before 2026.3.23 contains a replay identity vulnerability in Plivo V2 signature verification that allows attackers to bypass replay protection by modifying query parameters. The verification path derives replay keys from the full URL including query strings instead of the canonicalized...

ARuleCon: Agentic Security Rule Conversion

Security Information and Event Management SIEM systems make it possible for detecting intrusion anomalies in real-time manner by their applied security rules. However, the heterogeneity of vendor-specific rules e.g., Splunk SPL, Microsoft KQL, IBM AQL, Google YARA-L, and RSA ESA makes...

Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses under White-Box and Black-Box Threats

Concept drift and adversarial evasion are two major challenges for deploying machine learning-based malware detectors. While both have been studied separately, their combination, the adversarial robustness of drift-adaptive detectors, remains unexplored. We address this problem with AdvDA, a rece...

North Korean Hackers Pose as Trading Firm to Steal $285M from Drift

North Korean hackers UNC4736 posed as a trading firm for six months to infiltrate Drift Protocol, using social engineering tactics to steal $285M without suspicion...

Drift Loses $285 Million in Durable Nonce Social Engineering Attack Linked to DPRK

Solana-based decentralized exchange Drift has confirmed that attackers drained about $285 million from the platform during a security incident that took place on April 1, 2026. "Earlier today, a malicious actor gained unauthorized access to Drift Protocol through a novel attack involving durable...

VibeGuard: A Security Gate Framework for AI-Generated Code

"Vibe coding," in which developers delegate code generation to AI assistants and accept the output with little manual review, has gained rapid adoption in production settings. On March 31, 2026, Anthropic's Claude Code CLI shipped a 59.8 MB source map file in its npm package, exposing roughly...

Label-Efficient Training Updates for Malware Detection over Time

Machine Learning ML-based detectors are becoming essential to counter the proliferation of malware. However, common ML algorithms are not designed to cope with the dynamic nature of real-world settings, where both legitimate and malicious software evolve. This distribution drift causes models...

CVE-2026-32901

Affected software: OpenClaw prior to version 2026.3.2. Vulnerability type: semantic drift in node system.run approval hardening that rewrites wrapper argv, enabling execution of unintended local scripts when an attacker can influence argv and place malicious files in the approved working director...