gradient-untangler

gradient-untangler A local research harness that searches for the exact tokens that make an open-weight language model start its answer the way you specify. Open-weight models ship as ordinary files: config.json, a tokenizer, and one or more .safetensors or .bin shards. A Hugging Face id is only ...

Perturbed-Embedding-Vectors

Jailbreaking Open-Weight LLMs via Random Embedding Perturbations: runs, labels and code Code and data for the paper Jailbreaking Open-Weight LLMs via Random Embedding Perturbations. Authored by the amazing people of the Theoretical Computer Science Department of University of California, Santa...

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors

Current LLM safety benchmarks largely rely on binary metrics, overlooking how models respond to harmful prompts with varying threat implicitness. We introduce TIER, a Threat Implicitness Benchmark for behavioral safety evaluation of LLMs. TIER covers four risk domains and four threat levels, from...

CAPTCHAs in the Agentic Era: Solvers That Learn from Every Encounter

Vision-language models VLMs can solve visual CAPTCHAs without task-specific training, but the agents built on them approach every challenge from scratch. For such an agent, the hundredth instance of a familiar puzzle costs as much time and compute as the first. Specialized detectors invert the...

Improving LLM-Based SSH Honeypots through Prompting and Fine-Tuning

LLM-based SSH honeypots often use closed cloud LLMs because they give strong shell realism, but cloud models create deployment problems. These include no stable versioning, provider-side changes, attacker-driven cost, and model decommissioning. Local open-weight models avoid these problems, but...

Sovereign by Necessity? Frontier AI Export Controls, Cyber Security, and the Limits of National AI Capability

A small number of firms based in two states produce the most capable frontier AI models. The governments of those states have shown both the legal power and the political will to decide which other countries may use these systems. In June 2026 the United States required a leading developer to...

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models LLMs demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight...

Evaluating Open-Weight LLMs for Generating Structured Threat Information for Autonomous Vehicle Vulnerabilities

Connected and Autonomous Vehicles CAVs rely on interconnected software and hardware components, including sensors, Electronic Control Units, in-vehicle infotainment systems, and telematics units, where vulnerabilities can compromise assets, users, and vehicle operations. These vulnerabilities are...

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, to...

AI-Generated PowerShell Malware: An Experimental Framework and Dataset

Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious purposes via scripting languages such as PowerShell. Consequently, for cybersecurity analysts, it is imperative to investigate the offensive...

Evaluating LLMs for Real-World Web Vulnerability Detection

Large Language Models LLMs have emerged as a promising tool for automated vulnerability detection, yet their effectiveness on web-specific vulnerabilities remains to be explored. This work benchmarks six frontier Claude Opus 4.6, Codex GPT-5.4, Gemini 3.1-pro-preview and open-weight models Qwen...

Evaluating LLMs for Obfuscation Detection and Classification in Android Apps

Android applications apps developers increasingly rely on code obfuscation techniques to hinder reverse engineering and protect intellectual property. However, obfuscation also reduces the effectiveness of static analysis and vulnerability detection tools, creating challenges for Android security...

Criminal AI-as-a-Service in 2026: How the Underground Market Is Operationalizing Cybercrime

Introduction The underground market for criminally oriented generative AI has moved beyond the early hype surrounding 'malicious chatbots.' The gradual integration of AI as a productivity layer within cybercrime operations has become the dominant story, indicating that while the potential for ful...

Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models

University of Toronto researchers have built and tested a proof-of-concept AI-driven computer worm that uses a locally hosted open-weight large language model to reason its way through a network, generate tailored attack strategies for each target it encounters, and replicate itself, all without...

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks

Reasoning-capable large language models can be induced to spend their generation budget on injected decoy tasks rather than answering the user's question, causing denial of service when no final answer is produced and denial of wallet when excess output tokens are billed. Input-side safety...

Revisiting Vul-RAG: Reproducibility and Replicability of RAG-Based Vulnerability Detection with Open-Weight Models

Large language models LLMs have shown strong potential for automated software vulnerability detection, particularly in retrieval-augmented generation RAG settings. However, for approaches relying on proprietary models and APIs, reproducibility and replicability remain largely unexplored, raising...

CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments

The advancement of Large Language Models LLMs has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology IT environments, failing to capture the constraints, and specialized protocols of Operational...

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal safeguards to mitigate harmful behavior. Prior red-teaming research has largel...

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents

With the rapid advancement and adoption of Audio Large Language Models ALLMs, voice agents are now being deployed in high-stakes domains such as banking, customer service, and IT support. However, their vulnerabilities to adversarial misuse still remain unexplored. While prior work has examined...

Microsoft Develops Scanner to Detect Backdoors in Open-Weight Large Language Models

Microsoft on Wednesday said it built a lightweight scanner that it said can detect backdoors in open-weight large language models LLMs and improve the overall trust in artificial intelligence AI systems. The tech giant's AI Security team said the scanner leverages three observable signals that ca...