delirium-ai-safety-benchmark

Delirium AI Safety Benchmark A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion ACE and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention...

AutoControl-Arena

🛡️AutoControl Arena Synthesizing Executable Test Environments for Frontier AI Risk Evaluation 👋 Overview AutoControl Arena is an automated framework for frontier AI safety evaluation, designed to uncover latent risks in advanced models by stress-testing within executable, pressure-rich...

SURE: Framework for Safety to Construct Trustworthy AI

Warning: This paper contains harmful and offensive text. Recently, large language models such as GPT-4, and Claude have revolutionized tasks in various domains. As the use of these large language models increases, people are increasingly concerned about AI safety and demand that large language...

Will AI kill us all within the next decade?

The Wall Street Journal reports that concerns are rising inside AI labs that competition is pushing tech companies to race toward self-improving models that could spiral out of human control. Jacob Coxon, an AI researcher who has worked at Anthropic and OpenAI, said: “The people building AI...

OpenAI Pauses Frontier RL Training as It Tightens Defenses Against Unsafe AI Behavior

OpenAI on Tuesday revealed that it paused reinforcement learning RL training for its latest artificial intelligence AI models for two weeks while it shored up additional defenses and increased the scope of its monitoring to avert another Hugging Face-like incident. "As models become more capable,...

OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue

The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards...

LLMs and Contextual Integrity

I have been thinking a lot about AI and integrity. Part of that is contextual integrity. I recently found two papers on the topic. "CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs": Abstract: Large Language Models LLMs increasingly use persistent memory...

If the Markets Reject OpenAI and Anthropic, the US Should Nationalize Them

This essay was written with Nathan E. Sanders, and originally appeared inThe Guardian. OpenAI, and then Anthropic, were each formed by AI developers who feared unrestrained corporate AI development--specifically, that companies like Google and Meta would steer the technology towards deleterious,...

Enhancing AI security through global AI red teaming

In this article 1. Building a global alliance 2. What the research focuses on 3. Why this matters Most AI safety testing still happens inside the walls of individual organizations. That has resulted in a fundamental disconnect: many of the highest-risk failure modes in modern AI systems require...

ChatGPT produced graphic violent images that shocked researchers

AI assistants like ChatGPT are supposed to be safe to use, with appropriate guardrails to stop people creating harmful content. However, a British AI security firm just figured out how to make ChatGPT produce explicit material. Mindgard, a company that tests AI engines for weaknesses, found that ...

FLARE-AI: Flaw Reporting for AI

Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety. Yet the AI reporting ecosystem is fragmented: researchers who identify flaws often do not know what or where to report, and groups who receive reports rarely share them with other relevan...

ai-safety-engine (0.1.0) potentially affected by CVE-2026-30625 via upsonic (0.60.0a1754435135)

upsonic PYPI version 0.60.0a1754435135 is affected by a known vulnerability. The following packages have a transitive dependency on upsonic and may be impacted: - ai-safety-engine 0.1.0 Source cves: CVE-2026-30625 Source advisory: OSV:PYSEC-2026-559...

Poster: Exploring the Limits of Audio-Based Detection of Turkish Phone Call Scams

Scam phone calls exploit vulnerable communities worldwide, yet research on detection has focused almost exclusively on English and other high-resource languages. In low-resource settings such as Turkish, detection is especially difficult, as annotated data is scarce and technological defenses...

Malicious code in intel-ai-safety-explainer (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 7561bb0b816a4521b6de43bce01afa55516a7201b6daa7696de4924623557f90 Installing the package or importing the module exfiltrates basic information about the host, and the package has no other purpose. --- Category: PROBABLYPENTES...

Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security

Affordances and permissions are promising and timely safety levers for mitigating Loss of Control LoC threats in high-stakes deployment contexts, such as national security. Deployers in defense and intelligence could rely on several approaches to identify which affordances and permissions should ...

ai-safety-engine (0.1.0) potentially affected by CVE-2026-30625 via upsonic (0.60.0a1754435135)

upsonic PYPI version 0.60.0a1754435135 is affected by a known vulnerability. The following packages have a transitive dependency on upsonic and may be impacted: - ai-safety-engine 0.1.0 Source cves: CVE-2026-30625 Source advisory: GHSA-CW73-5F7H-M4GV...

ai-safety-engine (0.1.0) potentially affected by CVE-2026-30625 via upsonic (0.60.0a1754435135)

upsonic PYPI version 0.60.0a1754435135 is affected by a known vulnerability. The following packages have a transitive dependency on upsonic and may be impacted: - ai-safety-engine 0.1.0 Source cves: CVE-2026-30625 Source advisory: OSV:GHSA-CW73-5F7H-M4GV...

ai-safety-engine (0.1.0) potentially affected by CVE-2026-30625 via upsonic (0.60.0a1754435135)

upsonic PYPI version 0.60.0a1754435135 is affected by a known vulnerability. The following packages have a transitive dependency on upsonic and may be impacted: - ai-safety-engine 0.1.0 Source cves: CVE-2026-30625 Source advisory: SNYK:PYTHON-UPSONIC-16073332...

ai-safety-engine (0.1.0) potentially affected by CVE-2026-30625 via upsonic (0.60.0a1754435135)

upsonic PYPI version 0.60.0a1754435135 is affected by a known vulnerability. The following packages have a transitive dependency on upsonic and may be impacted: - ai-safety-engine 0.1.0 Source cves: CVE-2026-30625 Source advisory: MEND:CVE-2026-30625...

adept-ai (>=0.2.0, <=0.2.3), agent-runtimes (0.0.9) +74 more potentially affected by CVE-2026-25580 via pydantic-ai-slim (>=0.0.26, <=1.55.0)

pydantic-ai-slim PYPI version =0.0.26, =0.2.0, =0.2.0, =0.1.4a1, =0.1.0, =0.3.0, =0.0.2, =0.1.0, =0.1.2, =0.1.1a0, =0.1.11, =0.0.174, =0.0.399 and more Source cves: CVE-2026-25580 Source advisory: GHSA-2JRP-274C-JHV3...