Friday Squid Blogging: Do Squid Dream?

An exploration of the interesting question...

CyberExplorer: Benchmarking LLM Offensive Security Capabilities in a Real-World Attacking Simulation Environment

Real-world offensive security operations are inherently open-ended: attackers explore unknown attack surfaces, revise hypotheses under uncertainty, and operate without guaranteed success. Existing LLM-based offensive agent evaluations rely on closed-world settings with predefined goals and binary...

SecIC3: Customizing IC3 for Hardware Security Verification

Recent years have seen significant advances in using formal verification to check hardware security properties. Of particular practical interest are checking confidentiality and integrity of secrets, by checking that there is no information flow between the secrets and observable outputs. A...

HAL -- an Open-Source Framework for Gate-Level Netlist Analysis

HAL is an open-source framework for gate-level netlist analysis, an integral step in hardware reverse engineering. It provides analysts with an interactive GUI, an extensible plugin system, and APIs in both C++ and Python for rapid prototyping and automation. In addition, HAL ships with plugins f...

CVE-2025-9571

A remote code execution RCE vulnerability exists in Google Cloud Data Fusion. A user with permissions to upload artifacts to a Data Fusion instance can execute arbitrary code within the core AppFabric component. This could allow the attacker to gain control over the Data Fusion instance,...

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...

GAPS: Guiding Dynamic Android Analysis with Static Path Synthesis

Dynamically resolving method reachability in Android applications remains a critical and largely unsolved problem. Despite notable advancements in GUI testing and static call graph construction, current tools are insufficient for reliably driving execution toward specific target methods, especial...

EUVD-2025-198042

A command injection vulnerability exists in the MCP Data Science Server's reading-plus-ai/mcp-server-data-exploration 0.1.6 in the safeeval function src/mcpserverds/server.py:108. The function uses Python's exec to execute user-supplied scripts but fails to restrict the builtins dictionary in the...

MCP Server for Data Exploration 安全漏洞

MCP Server for Data Exploration is an MCP server for reading-plus-ai individual developers. A security vulnerability exists in MCP Data Science Server version 0.1.6 that stems from the safeeval function not restricting the builtins dictionary, which could lead to arbitrary code execution...

EUVD-2005-2814

Malware in sbrugna...

LegalSim: Multi-Agent Simulation of Legal Systems for Discovering Procedural Exploits

We present LegalSim, a modular multi-agent simulation of adversarial legal proceedings that explores how AI systems can exploit procedural weaknesses in codified rules. Plaintiff and defendant agents choose from a constrained action space for example, discovery requests, motions, meet-and-confer,...

SCANNER-INURLBR

This is an offensive tool for web application vulnerability scanning. The tool, INURLBR, is designed to perform advanced searches in search engines to exploit GET/POST capturing emails and URLs, with an internal custom validation junction for each target/URL found. It is written in PHP and can ru...

LogGuardQ: a Cognitive-Enhanced Reinforcement Learning Framework for Cybersecurity Anomaly Detection in Security Logs

Reinforcement learning RL has transformed sequential decision-making, but traditional algorithms like Deep Q-Networks DQNs and Proximal Policy Optimization PPO often struggle with efficient exploration, stability, and adaptability in dynamic environments. This study presents LogGuardQ Adaptive Lo...

MultiFuzz: a Dense Retrieval-Based Multi-Agent System for Network Protocol Fuzzing

Traditional protocol fuzzing techniques, such as those employed by AFL-based systems, often lack effectiveness due to a limited semantic understanding of complex protocol grammars and rigid seed mutation strategies. Recent works, such as ChatAFL, have integrated Large Language Models LLMs to guid...

HEIR: a Universal Compiler for Homomorphic Encryption

This work presents Homomorphic Encryption Intermediate Representation HEIR, a unified approach to building homomorphic encryption HE compilers. HEIR aims to support all mainstream techniques in homomorphic encryption, integrate with all major software libraries and hardware accelerators, and...

Next-Generation Quantum Neural Networks: Enhancing Efficiency, Security, and Privacy

This paper provides an integrated perspective on addressing key challenges in developing reliable and secure Quantum Neural Networks QNNs in the Noisy Intermediate-Scale Quantum NISQ era. In this paper, we present an integrated framework that leverages and combines existing approaches to enhance...

Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance

Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' susceptibility to diverse jailbreak attacks. Concurrently, inference scaling has significantly advanced LLM reasoning...

CVE-2024-5550

In h2oai/h2o-3 version 3.40.0.4, an exposure of sensitive information vulnerability exists due to an arbitrary system path lookup feature. This vulnerability allows any remote user to view full paths in the entire file system where h2o-3 is hosted. Specifically, the issue resides in the Typeahead...

Securing Generative AI: Navigating Risk and Building Resilience

Running short on time but still want to stay in the know? Well, we’ve got you covered! We’ve condensed all the key takeaways into a handy audio summary. Our AI-driven podcasts are fit for on the go. Click right here to hear it all on CAASM & CDMB Inefficiencies! Generative AI has changed the way ...

Neural-Inspired Advances in Integral Cryptanalysis

The study by Gohr et.al at CRYPTO 2019 and sunsequent related works have shown that neural networks can uncover previously unused features, offering novel insights into cryptanalysis. Motivated by these findings, we employ neural networks to learn features specifically related to integral...