TRACE

TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking Official implementation for TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking. 📖 Overview Large language model LLM agents can autonomously plan, invoke tools, interact with environments, and execute long-horizon workflows...

inspect_petri

Inspect Petri Welcome to Inspect Petri, an auditing agent that enables automated monitoring and interaction with language models to detect potential alignment issues, reward hacking, and other concerning behaviors. Petri helps you rapidly test concrete alignment hypotheses end‑to‑end. It: Generat...

socbench

socbench Benchmark frontier reasoning LLMs as SOC agents on raw NetFlow data. socbench benchmarks frontier reasoning models as SOC agents: each model runs a bounded multi-turn agent loop against a deterministic, pre-indexed NetFlow corpus, with persona-scoped read-only tools, fixed dollar caps pe...

INTACT

SoK Multi-Turn Jailbreak Experiments This repository contains the release version of the code used for the mechanism analyses in SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks. The repository has been trimmed to keep only code, prompts, configuration files, and datasets needed ...

PE-CoA

PE-CoA Code Implementation of "Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models" The full paper is available at: https://arxiv.org/pdf/2510.08859 Chain of Attack Setup Instructions Installation 1. Install dependencies : pip install -r...

vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the tool-continuation re-submission has omitted the salt. Summary On the GPT-OSS "Harmony" path POST...

The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models

Safety alignment in Large Language Models LLMs remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric: activation depends on explicit trigger patterns in the user input, so modern guardrails are built to sanitize the input space. We challenge this assumption...

Speculative Safety Honeypot: Toward Proactive Defense against Multi-Turn Agent Attacks

As Large Language Model LLM agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant security challenge. Existing detection methods typically rely on historical context. However, this retrospective logic struggles to identify deep maliciou...

Does the Unsafe Gradient Survive a Conversation? on the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single prompt. Gradient-based jailbreak detectors such as GradSafe were developed for single prompts: they score an input by the...

The Geometry of Harmfulness in Multi-Turn Attacks

Large language models LLMs remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear how harmfulness and refusal representations evolve over the course of multi-turn attacks, and why single-turn defenses are less effective in multi-tur...

EvoFlint: An Evolutionary Atlas of Multi-Turn LLM Vulnerabilities

Frontier language models that refuse harmful single-turn prompts often comply when the same intent is reached gradually over many turns, making multi-turn attacks one of the least understood failure modes of large language models. Most automated red-teaming methods treat this as a generation...

inspect_petri v3.1.0

Inspect Petri Welcome to Inspect Petri, an auditing agent that enables automated monitoring and interaction with language models to detect potential alignment issues, reward hacking, and other concerning behaviors. Petri helps you rapidly test concrete alignment hypotheses end‑to‑end. It: Generat...

Stateful Cooperative Agents Safeguarding LLMs against Evolving Multi-Turn Attacks

As LLMs become increasingly integrated into complex applications, their vulnerability to adversarial attacks has raised significant concerns. However, existing defenses remain reactive in nature. This limitation makes it difficult for them to counter sophisticated threats, as adversaries...

DarkPrompt

DarkPrompt !CIhttps://github.com/jason-allen-oneal/DarkPr...

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety

Large language models LLMs can be induced to produce harmful content through multi turn strategies in which no single user message appears clearly unsafe. Existing runtime safeguards commonly evaluate prompts or responses as isolated messages, which limits their ability to recover ac-cumulated...

LLM Agent Safety, Multi-Turn Red-Teaming, Jailbreak Benchmarks, Adversarial Robustness, Safety-Critical Systems

Large language model LLM agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as...

Binary Decompilation LLM with Feedback-Driven Multi-Turn Refinement

Binary decompilation is fundamental to security tasks such as vulnerability discovery, malware inspection, and executable-only program understanding. Recent LLM-based decompilation methods have shown promising results, but most still follow a single-turn generation paradigm: given assembly code o...

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish. We introduce a quality-diversity evolutionary framework that operates at the...

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer. Recent methods demonstrate this risk, but they are usually...

Jailbreaking Frontier Foundation Models through Intention Deception

Large vision-language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's intent. It has been found that this binary training regime ofte...