相关论文: Predict, Don't React: Value-Based Safety Forecasti…

Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks. However, a critical challenge remains in that they sometimes generate factually incorrect answers. To address this, while many…

Recent advances in Streaming Video Understanding has enabled a new interaction paradigm where models respond proactively to user queries. Current proactive VideoLLMs rely on per-frame triggering decision making, which suffers from an…

Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety frameworks and guardrails, current protective measures exhibit…

Although modern LLMs are aligned with human values during post-training, robust moderation remains essential to prevent harmful outputs at deployment time. Existing approaches suffer from performance-efficiency trade-offs and are difficult…

The rapid advancement of large language models (LLMs) has led to significant improvements in their capabilities, but also to increased concerns about their alignment with human values and intentions. Current alignment strategies, including…

Truly multilingual safety moderation efforts for Large Language Models (LLMs) have been hindered by a narrow focus on a small set of languages (e.g., English, Chinese) as well as a limited scope of safety definition, resulting in…

Recently, HTTP-Based Adaptive Streaming has become the de facto standard for video streaming over the Internet. It allows the client to adapt media characteristics to varying network conditions in order to maximize Quality of Experience…

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

Non-autoregressive (NAR) modeling has gained significant interest in speech processing since these models achieve dramatically lower inference time than autoregressive (AR) models while also achieving good transcription accuracy. Since NAR…

Recently, web-based Large Language Model (LLM) agents autonomously perform increasingly complex tasks, thereby bringing significant convenience. However, they also amplify the risks of malicious misuse cases such as unauthorized collection…

Existing jailbreak defense paradigms primarily rely on static detection of prompts, outputs, or internal states, often neglecting the dynamic evolution of risk during decoding. This oversight leaves risk signals embedded in decoding…

Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended…

Social platforms have revolutionized information sharing, but also accelerated the dissemination of harmful and policy-violating content. To ensure safety and compliance at scale, moderation systems must go beyond efficiency and offer…

Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, safety policies are increasingly specified at inference time by users, organizations, or…

Given a stream of heterogeneous graphs containing different types of nodes and edges, how can we spot anomalous ones in real-time while consuming bounded memory? This problem is motivated by and generalizes from its application in security…

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

Platform content moderation applies explicit policy rules and context-dependent conditions to decide whether user content is allowed, restricted, or removed. A correct moderation outcome must therefore depend on which rules a case…

Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yielding safer-on-paper yet less useful systems. This work introduces Guardian-as-an-Advisor…

Fault tolerance is critical for distributed stream processing systems, yet achieving error-free fault tolerance often incurs substantial performance overhead. We present AF-Stream, a distributed stream processing system that addresses the…

The adoption of Generative AI (GenAI) in applications inevitably comes with the expansion of the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim…