Not the Coyote, but the Road Runner: The Reality of Autonomous AI Attacks

Autonomous AI security threats aren't novel super-weapons. They're relentless, low-tech attacks that never stop. Learn why traditional defenses fail...

SkillShield: Prompt-Space Security Skills for LLM Coding Agents

A coding agent edits files and executes shell commands with its developer's privileges, allowing malicious requests to translate directly into harmful actions or functional malware. Existing defenses have complementary limitations: weight-level alignment is unavailable to API-only deployers,...

Adversarial Training of Linear Models under Stealthy Attacks

Predictive models are widely used in many fields, but are vulnerable to false data injection attacks. To address this, detection schemes and adversarial training have been proposed, but such approaches lack guarantees against stealthy attacks. We therefore propose a detector-based switched model,...

Defending Network Intrusion Detection Systems Based on Graph Neural Networks against Structural Adversarial Attacks

Graph Neural Networks GNNs represent a promising solution for Machine Learning ML based Network Intrusion Detection Systems NIDS, thanks to their ability to leverage both network flow features and topological patterns. While GNN classifiers demonstrate superior robustness against feature-based...

⚡ Weekly Recap: AI-Powered PLC Attacks, GitLab Attacks, Stripe Key Leaks and More

A package gets installed. A login prompt opens. A box sits exposed to the internet. Nothing looks unusual yet. That’s roughly the mood this week. Trusted tools turn hostile, old weak spots get fresh attention, AI makes exploit work cheaper, and researchers keep finding attacks that sound harder...

UAT-10147 Uses AI to Scale Server Attacks, Deploys SPECTRE With EDR Bypass and Linux Rootkit

Cybersecurity researchers have disclosed details of a Chinese-speaking cybercrime group dubbed UAT-10147 that's targeting Windows and Linux web servers globally across the education, media, technology, and gaming sectors. The vast majority of the targets are located in Brazil, Bolivia, China,...

Deconstructing the Architecture of AI-Orchestrated Web Attacks

...

UAT-10147: Chinese-speaking adversary integrates agentic AI into post-compromise operations

Cisco Talos identified UAT-10147 targeting Windows and Linux web servers globally, impacting organizations in government, education, media, technology, and gaming sectors. The actor leveraged publicly disclosed vulnerabilities to gain initial access at scale. UAT-10147 integrated AI-driven toolin...

Hackers Compromised 14,500+ Dahua Devices Using Credential Attacks, Auth Bypasses, and P2P

Cybersecurity researchers at Hunt.io have disclosed details of a campaign that they say compromised more than 14,530 Dahua devices between June 17 and July 22, 2026, using credential attacks, two authentication-bypass flaws, and a peer-to-peer P2P relay technique. The activity, codenamed Operatio...

CVE-2026-54739: Observable Response Discrepancy

Lemmy is a link aggregator and forum for the fediverse. Prior to 0.19.19 and 1.0.0-beta.1, Lemmy's login endpoint in crates/api/api/src/localuser/login.rs returns different errors depending on whether the usernameoremail value exists. LocalUserView::findbyemailorname propagates a NotFound respons...

Allocation of Resources Without Limits or Throttling

Overview openssl-encrypt is an A package for secure file encryption and decryption based on modern ciphers using heavy-compute-load chaining of hashing and KDF to generate strong encryption password based on users provided password to ensure secure encryption of files Affected versions of this...

Improper Verification of Cryptographic Signature

Overview openssl-encrypt is an A package for secure file encryption and decryption based on modern ciphers using heavy-compute-load chaining of hashing and KDF to generate strong encryption password based on users provided password to ensure secure encryption of files Affected versions of this...

PYSEC-2026-3765

opensslencrypt versions before 1.4.0 use HKDF with no salt and static info parameter in key normalization functions, reducing entropy extraction and determinism. Attackers can exploit predictable key derivation with identical inputs to weaken cryptographic security against multi-target attacks...

CVE-2026-74889 openssl_encrypt before 1.4.0 Weak Key Derivation via HKDF

opensslencrypt versions before 1.4.0 use HKDF with no salt and static info parameter in key normalization functions, reducing entropy extraction and determinism. Attackers can exploit predictable key derivation with identical inputs to weaken cryptographic security against multi-target attacks...

CVE-2026-74889 openssl_encrypt before 1.4.0 Weak Key Derivation via HKDF

opensslencrypt versions before 1.4.0 use HKDF with no salt and static info parameter in key normalization functions, reducing entropy extraction and determinism. Attackers can exploit predictable key derivation with identical inputs to weaken cryptographic security against multi-target attacks...

CVE-2026-74889

The openssl_encrypt library (PHP package) before version 1.4.0 uses HKDF with no salt and a static info parameter in its key normalization functions, producing deterministic, low-entropy derived keys. Attackers with identical inputs can predict derived keys, weakening cryptographic security again...

augustus v0.14.20

Augustus - LLM vulnerability scanner for prompt injection, jailbreak, and adversarial attack testing Augustus - LLM Vulnerability Scanner Test large language models against 210+ adversarial attacks covering prompt injection, jailbreaks, encoding exploits, and data extraction. Augustus is a Go-bas...

CVE-2026-74889: Inadequate Encryption Strength

opensslencrypt versions before 1.4.0 use HKDF with no salt and static info parameter in key normalization functions, reducing entropy extraction and determinism. Attackers can exploit predictable key derivation with identical inputs to weaken cryptographic security against multi-target attacks...

Assessing Attack Surfaces in Generative Search Engines through Publisher Attributes: A Case Study in Political Domains

We characterize the attack surface of generative search engines GSEs against poisoning attacks in the political domain, from the perspectives of citation selection and personalization. GSEs integrate web search and answer generation with user preferences and backgrounds using large language model...

guarddog v3.2.0

GuardDog GuardDog is a CLI tool that identifies malicious PyPI and npm packages, Go modules, Rust crates, RubyGems, GitHub actions, or VSCode extensions. It runs static analysis on package source code through YARA rules and analyzes package metadata to detect supply chain attacks. What makes...