REVIEW 17 cited by
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
read the original abstract
Multi-turn interactions with language models (LMs) pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and diversity remain among the key challenges of multi-turn red-teaming. To address these challenges, we present X-Teaming, a scalable framework that systematically explores how seemingly harmless interactions escalate into harmful outcomes and generates corresponding attack scenarios. X-Teaming employs collaborative agents for planning, attack optimization, and verification, achieving state-of-the-art multi-turn jailbreak effectiveness and diversity with success rates up to 98.1% across representative leading open-weight and closed-source models. In particular, X-Teaming achieves a 96.2% attack success rate against the latest Claude 3.7 Sonnet model, which has been considered nearly immune to single-turn attacks. Building on X-Teaming, we introduce XGuard-Train, an open-source multi-turn safety training dataset that is 20x larger than the previous best resource, comprising 30K interactive jailbreaks, designed to enable robust multi-turn safety alignment for LMs. Our work offers essential tools and insights for mitigating sophisticated conversational attacks, advancing the multi-turn safety of LMs.
Forward citations
Cited by 17 Pith papers
-
Do LLMs Know Their Vulnerable Scenarios?
Scenario jailbreaks suppress refusal via internal concept directions; Concept2Scenario attributes those concepts with SAEs and turns them into transferable natural-language attack scenarios.
-
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments
AgentCanary introduces an Entry × Impact risk taxonomy, high-fidelity real tool environments with persistent state, and multi-dimensional trajectory evaluation to assess AI agent security across models and attacks.
-
Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
A single safety demonstration appended at inference time mitigates many-shot jailbreak attacks by counteracting implicit malicious fine-tuning on harmful examples.
-
Conjunctive Prompt Attacks in Multi-Agent LLM Systems
Conjunctive prompt attacks split adversarial elements across agents and routing paths in multi-agent LLM systems, evading isolated defenses and succeeding through topology-aware optimization.
-
SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits
SelfGrader detects LLM jailbreaks by interpreting logit distributions on numerical tokens with a dual maliciousness-benignness score, cutting attack success rates up to 22.66% while using up to 173x less memory and 26...
-
SoK: Exposing the Generation and Detection Gaps in LLM-Generated Phishing
This SoK paper introduces a nine-stage taxonomy for LLM guardrail breaches in phishing, characterizes evasion and manipulation tactics, and identifies a dynamic-offense versus static-defense asymmetry.
-
AMT-X: Phase-Structured Multi-Turn Red-Teaming with Checklist-Gated Evaluation
A phase-structured multi-turn red-team framework reports 97.6–100% lenient ASR but only 66.7–78.6% full actionable ASR on six frontier LLMs, with success strongly depth-dependent.
-
Addressing Over-Refusal in LLMs with Competing Rewards
SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.
-
Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
Web retrieval degrades safety alignment in LLM agents, with relevance activating vulnerabilities including a Safe Source Paradox where oppositional content increases harmful compliance.
-
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
MT-JailBench is a modular benchmark that standardizes evaluation of multi-turn jailbreaks to identify key success drivers and enable stronger combined attacks.
-
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
TurnGate uses a new multi-turn intent dataset to detect the harm-enabling closure point in dialogues, outperforming baselines with low over-refusal and generalizing across domains.
-
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
TurnGate identifies the critical turn in multi-turn dialogues where a response would complete hidden malicious intent, outperforming baselines on the new MTID dataset while keeping over-refusal low.
-
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
MultiBreak is a large diverse multi-turn jailbreak benchmark that achieves substantially higher attack success rates on LLMs than prior datasets and reveals topic-specific vulnerabilities in multi-turn settings.
-
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.
-
SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits
SelfGrader grades query harmfulness from anchored numerical-token logits plus PAC-guided dual-perspective ICL, claiming strong jailbreak detection with low FPR and latency.
-
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
EvoSynth evolves code-based jailbreak algorithms via multi-agent self-correction, reaching 85.5% ASR on Claude-Sonnet-4.5 and 95.9% average across targets with greater diversity.
-
The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.