Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores inference-time defenses, existing methods rely on static interventions on intermediate representations, which often degrade generation quality and impair adherence to task instructions, reducing system usability in EI settings. We propose a dynamic defense framework. For each EI inference request, we dynamically construct a task-specific safety-semantic subspace, project its hidden state to the most relevant direction, and apply SLERP rotation for adaptive safety control. At comparable defense success rates, our method preserves generation quality, improves usability, reduces tuning cost, and strengthens robustness in EI scenarios.

Services powered by large language models (LLMs) provide powerful text generation capabilities, but accessing sensitive user inputs raises serious privacy concerns. Trusted Execution Environments (TEEs) provide a secure computation environment, enabling sensitive inputs to be safely processed. However, directly deploying high-capacity LLMs in TEEs is often prohibitively expensive due to computation and memory constraints. To reconcile privacy, efficiency, and generation quality, we propose CoTrust, a privacy-preserving collaborative inference framework that combines LLMs with small language models (SLMs) inside TEE. CoTrust uses multiple de-identified views to let the LLM produce a consensus scaffold capturing answer reasoning without exposing private information, which the SLM then grounds in the full input to generate the final response. Experiments on multiple question answering and summarization benchmarks show that CoTrust approaches the performance of unconstrained LLMs, outperforms existing privacy-preserving baselines, and maintains strong privacy protection, while remaining efficient in a TDX-based TEE implementation.

As open-source large language models (LLMs) become increasingly powerful, they are rapidly evolving into Agentic LLMs capable of automating complex daily tasks. However, this paradigm shift entails severe security risks, as the agents’ necessary integration with external real-time data sources creates a direct pathway for indirect prompt injection (IPI) attacks. Existing attack methods are limited by their reliance on static patterns and evaluation on simple language models, failing to address the fast-evolving nature of modern Agentic LLMs. We introduce AdapTools, a novel adaptive IPI attack framework that selects stealthier attack tools and generates adaptive attack prompts to create a rigorous security evaluation environment. Our approach comprises two key components: (1) Adaptive Attack Strategy Construction, which develops transferable adversarial strategies for prompt optimization, and (2) Attack Enhancement, which identifies stealthy tools capable of circumventing task-relevance defenses. Comprehensive experiments on both open-source and commercial agentic LLMs show that AdapTools achieves a per-model average improvement of 2.08× in attack success rate over the strongest baseline under state-of-the-art defenses (MELON, Pi-Detector), with gains reaching up to 3.06× on the most resistant reasoning agents. The framework further transfers to black-box commercial agents (GPT, Qwen, Gemini), with ASR ranging from 4.2 to 20.3 (peak on the in-family Qwen-MAX), exposing systematic vulnerabilities in modern Agentic LLMs.

Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model’s operational capability boundary, leading to long but unproductive reasoning. In this paper, we study whether LRMs expose early signals predictive of such cases, and whether these signals can be used to mitigate unproductive reasoning. In black-box settings, we find that reasoning expressions contain failure-predictive signals. In white-box settings, we show that the hidden states of the last input token contain information that is predictive of whether a question will not be solved correctly under our evaluation setup. Building on these observations, we propose two test-time monitoring strategies: reasoning expression monitoring and hidden states monitoring, that reduce token usage by 62.7–93.6%, substantially improving efficiency and reliability while largely preserving accuracy.

Advanced LLMs have achieved near-ceiling instruction-following accuracy on benchmarks such as IFEval. However, these impressive scores do not necessarily translate to reliable services in real-world use, where users often vary their phrasing, contextual framing, and task formulations. In this paper, we study nuance-oriented reliability: whether models exhibit consistent competence across cousin prompts that convey analogous user intents but with subtle nuances. To quantify this, we introduce a new metric, reliable@k, and develop an automated pipeline that generates high-quality cousin prompts via data augmentation. Building upon this, we construct IFEval++ for systematic evaluation. Across 20 proprietary and 26 open-source LLMs, we find that current models exhibit substantial insufficiency in nuance-oriented reliability—their performance can drop by up to 61.8% with nuanced prompt modifications. What’s more, we characterize it and explore three potential improvement recipes. Our findings highlight nuance-oriented reliability as a crucial yet underexplored next step toward more dependable and trustworthy LLM behavior. Our code and benchmark are accessible: https://github.com/jianshuod/IFEval-pp.

Large language models (LLMs) exhibit prompt leakage vulnerabilities, where they may be coaxed into revealing system prompts embedded in LLM services, raising intellectual property and confidentiality concerns. An intriguing question arises: Do LLMs genuinely internalize prompt leakage intents in their hidden states before generating tokens? In this work, we use probing techniques to capture LLMs’ intent-related internal representations and confirm that the answer is yes. We start by comprehensively inducing prompt leakage behaviors across diverse system prompts, attack queries, and decoding methods. We develop a hybrid labeling pipeline, enabling the identification of broader prompt leakage behaviors beyond mere verbatim leaks. Our results show that a simple linear probe can predict prompt leakage risks from pre-generation hidden states without generating any tokens. Across all tested models, linear probes consistently achieve 90%+ AUROC, even when applied to new system prompts and attacks. Understanding the model internals behind prompt leakage drives practical applications, including intention-based detection of prompt leakage risks. Code is available at: https://github.com/jianshuod/Probing-leak-intents.