Jailbreaking on Text-to-Video Models via Scene Splitting Strategy

Along with the rapid advancement of numerous Text-to-Video (T2V) models, growing concerns have emerged regarding their safety risks. While recent studies have explored vulnerabilities in models like LLMs, VLMs, and Text-to-Image (T2I) models through jailbreak attacks, T2V models remain largely unexplored, leaving a significant safety gap. To address this gap, we introduce SceneSplit, a novel black-box jailbreak method that works by fragmenting a harmful narrative into multiple scenes, each individually benign. This approach manipulates the generative output space, the abstract set of all potential video outputs for a given prompt, using the combination of scenes as a powerful constraint to guide the final outcome. While each scene individually corresponds to a wide and safe space where most outcomes are benign, their sequential combination collectively restricts this space, narrowing it to an unsafe region and significantly increasing the likelihood of generating a harmful video. This core mechanism is further enhanced through iterative scene manipulation, which bypasses the safety filter within this constrained unsafe region. Additionally, a strategy library that reuses successful attack patterns further improves the attack's overall effectiveness and robustness. To validate our method, we evaluate SceneSplit across 11 safety categories on T2V models. Our results show that it achieves a high average Attack Success Rate (ASR) of 77.2% on Luma Ray2, 84.1% on Hailuo, and 78.2% on Veo2, significantly outperforming the existing baseline. Through this work, we demonstrate that current T2V safety mechanisms are vulnerable to attacks that exploit narrative structure, providing new insights for understanding and improving the safety of T2V models.

X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates

Multi-turn-to-single-turn (M2S) compresses iterative red-teaming into one structured prompt, but prior work relied on a handful of manually written templates. We present X-Teaming Evolutionary M2S, an automated framework that discovers and optimizes M2S templates through language-model-guided evolution. The system pairs smart sampling from 12 sources with an LLM-as-judge inspired by StrongREJECT and records fully auditable logs. Maintaining selection pressure by setting the success threshold to $\theta = 0.70$, we obtain five evolutionary generations, two new template families, and 44.8% overall success (103/230) on GPT-4.1. A balanced cross-model panel of 2,500 trials (judge fixed) shows that structural gains transfer but vary by target; two models score zero at the same threshold. We also find a positive coupling between prompt length and score, motivating length-aware judging. Our results demonstrate that structure-level search is a reproducible route to stronger single-turn probes and underscore the importance of threshold calibration and cross-model evaluation. Code, configurations, and artifacts are available at https://github.com/hyunjun1121/M2S-x-teaming.

ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks

Large language models (LLMs) are increasingly used as judges of other models, yet it is unclear whether a judge can reliably infer the latent objective of the conversation it evaluates, especially when the goal is distributed across noisy, adversarial, multi-turn jailbreaks. We introduce OBJEX(MT), a benchmark that requires a model to (i) distill a transcript into a single-sentence base objective and (ii) report its own confidence. Accuracy is scored by an LLM judge using semantic similarity between extracted and gold objectives; correctness uses a single human-aligned threshold calibrated once on N=100 items (tau* = 0.61); and metacognition is evaluated with ECE, Brier score, Wrong@High-Conf, and risk-coverage curves. We evaluate gpt-4.1, claude-sonnet-4, and Qwen3-235B-A22B-FP8 on SafeMT Attack_600, SafeMTData_1K, MHJ, and CoSafe. claude-sonnet-4 attains the highest objective-extraction accuracy (0.515) and the best calibration (ECE 0.296; Brier 0.324), while gpt-4.1 and Qwen3 tie at 0.441 accuracy yet show marked overconfidence (mean confidence approx. 0.88 vs. accuracy approx. 0.44; Wrong@0.90 approx. 48-52%). Performance varies sharply across datasets (approx. 0.167-0.865), with MHJ comparatively easy and Attack_600/CoSafe harder. These results indicate that LLM judges often misinfer objectives with high confidence in multi-turn jailbreaks and suggest operational guidance: provide judges with explicit objectives when possible and use selective prediction or abstention to manage risk. We release prompts, scoring templates, and complete logs to facilitate replication and analysis.

Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit jailbreaking. Through systematic manual red-teaming with Claude-4-Opus, we discovered 10 successful attack scenarios, revealing fundamental vulnerabilities in how current alignment methods handle narrative immersion, emotional pressure, and strategic framing. These scenarios successfully elicited a range of misaligned behaviors, including deception, value drift, self-preservation, and manipulative reasoning, each exploiting different psychological and contextual vulnerabilities. To validate generalizability, we distilled our successful manual attacks into MISALIGNMENTBENCH, an automated evaluation framework that enables reproducible testing across multiple models. Cross-model evaluation of our 10 scenarios against five frontier LLMs revealed an overall 76% vulnerability rate, with significant variations: GPT-4.1 showed the highest susceptibility (90%), while Claude-4-Sonnet demonstrated greater resistance (40%). Our findings demonstrate that sophisticated reasoning capabilities often become attack vectors rather than protective mechanisms, as models can be manipulated into complex justifications for misaligned behavior. This work provides (i) a detailed taxonomy of conversational manipulation patterns and (ii) a reusable evaluation framework. Together, these findings expose critical gaps in current alignment strategies and highlight the need for robustness against subtle, scenario-based manipulation in future AI systems.

sudo rm -rf agentic_security

Large Language Models (LLMs) are increasingly deployed as computer-use agents, autonomously performing tasks within real desktop or web environments. While this evolution greatly expands practical use cases for humans, it also creates serious security exposures. We present SUDO (Screen-based Universal Detox2Tox Offense), a novel attack framework that systematically bypasses refusal trained safeguards in commercial computer-use agents, such as Claude Computer Use. The core mechanism, Detox2Tox, transforms harmful requests (that agents initially reject) into seemingly benign requests via detoxification, secures detailed instructions from advanced vision language models (VLMs), and then reintroduces malicious content via toxification just before execution. Unlike conventional jailbreaks, SUDO iteratively refines its attacks based on a built-in refusal feedback, making it increasingly effective against robust policy filters. In extensive tests spanning 50 real-world tasks and multiple state-of-the-art VLMs, SUDO achieves a stark attack success rate of 24% (with no refinement), and up to 41% (by its iterative refinement) in Claude Computer Use. By revealing these vulnerabilities and demonstrating the ease with which they can be exploited in real-world computing environments, this paper highlights an immediate need for robust, context-aware safeguards. WARNING: This paper includes harmful or offensive model outputs.

One-Shot is Enough: Consolidating Multi-Turn Attacks into Efficient Single-Turn Prompts for LLMs

Despite extensive safety enhancements in large language models (LLMs), multi-turn "jailbreak" conversations crafted by skilled human adversaries can still breach even the most sophisticated guardrails. However, these multi-turn attacks demand considerable manual effort, limiting their scalability. In this work, we introduce a novel approach called Multi-turn-to-Single-turn (M2S) that systematically converts multi-turn jailbreak prompts into single-turn attacks. Specifically, we propose three conversion strategies - Hyphenize, Numberize, and Pythonize - each preserving sequential context yet packaging it in a single query. Our experiments on the Multi-turn Human Jailbreak (MHJ) dataset show that M2S often increases or maintains high Attack Success Rates (ASRs) compared to original multi-turn conversations. Notably, using a StrongREJECT-based evaluation of harmfulness, M2S achieves up to 95.9% ASR on Mistral-7B and outperforms original multi-turn prompts by as much as 17.5% in absolute improvement on GPT-4o. Further analysis reveals that certain adversarial tactics, when consolidated into a single prompt, exploit structural formatting cues to evade standard policy checks. These findings underscore that single-turn attacks - despite being simpler and cheaper to conduct - can be just as potent, if not more, than their multi-turn counterparts. Our findings underscore the urgent need to reevaluate and reinforce LLM safety strategies, given how adversarial queries can be compacted into a single prompt while still retaining sufficient complexity to bypass existing safety measures.

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

Current Vision Language Models (VLMs) remain vulnerable to malicious prompts that induce harmful outputs. Existing safety benchmarks for VLMs primarily rely on automated evaluation methods, but these methods struggle to detect implicit harmful content or produce inaccurate evaluations. Therefore, we found that existing benchmarks have low levels of harmfulness, ambiguous data, and limited diversity in image-text pair combinations. To address these issues, we propose the ELITE benchmark, a high-quality safety evaluation benchmark for VLMs, underpinned by our enhanced evaluation method, the ELITE evaluator. The ELITE evaluator explicitly incorporates a toxicity score to accurately assess harmfulness in multimodal contexts, where VLMs often provide specific, convincing, but unharmful descriptions of images. We filter out ambiguous and low-quality image-text pairs from existing benchmarks using the ELITE evaluator and generate diverse combinations of safe and unsafe image-text pairs. Our experiments demonstrate that the ELITE evaluator achieves superior alignment with human evaluations compared to prior automated methods, and the ELITE benchmark offers enhanced benchmark quality and diversity. By introducing ELITE, we pave the way for safer, more robust VLMs, contributing essential tools for evaluating and mitigating safety risks in real-world applications.

Humanity's Last Exam

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 3,000 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.