Category
1,065 papers
Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription decisions are inherently made on incomplete information. This causal constraint serves as an information bottleneck on attackers, significantly limiting attack pe...
IntraGuard is proposed, a black-box, venue-agnostic defense framework grounded in the structural--visual decoupling inherent to the PDF that achieves a defense success rate of up to 84%, while preserving peer-review invariance for human reviewers.
This paper presents GAAP (Guaranteed Accounting for Agent Privacy), an execution environment for AI agents that guarantees confidentiality for private user data deterministically, without trusting the agent with private user data, and without requiring any AI model or the user prompt to be free of attacks.
Automated Code Review (ACR) systems integrating Large Language Models (LLMs) are increasingly adopted in software development workflows, ranging from interactive assistants to autonomous agents in CI/CD pipelines. In this paper, we study how LLM-based vulnerability detection in ACR is affected by the framing effect: th...
Reach audiences
Advertise in front of researchers, engineers, and readers.
The findings highlight evaluation rubrics as a sensitive and manipulable control interface, revealing a system-level alignment risk that extends beyond evaluator reliability alone.
The TaCCS-DFA framework is designed, which combines online low-rank Fisher subspace estimation with an adaptive gating mechanism to enable efficient task-oriented fusion, and significantly tightens the upper bound on the output error.
Malicious AI causing harm to humans is not just a Hollywood fantasy. Indeed, as highly capable models such as Claude Mythos emerge and agent systems like OpenClaw rapidly spread, the question of how to stop an AI that acts maliciously -- whether by design or by accident -- has become urgent. To address this, we propose...
Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often collected from diverse and...
Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can transfer backdoors to various downstream tasks. In this paper, we introduce $\mathtt{maxEntropy}$, an entropy-based poisoning filter that mitiga...
VLoc Benchmark results establish vulnerability localization as a distinct repository-scale capability and provide a setting for studying both how security agents search for vulnerable code and when they should refrain from reporting it.
Rising societal and lifestyle complexity has been linked to a growing prevalence of mental distress worldwide. Educational institutions, workplaces, clinics, etc. collect large volumes of mental health survey data to understand and reduce this burden. Collaborative analysis of such data could yield effective generaliza...
Pretrained world models, learned simulators that encode an observation into a latent state and predict how it evolves under actions, are beginning to be reused as off-the-shelf dynamics backbones for control, like pretrained encoders and language models are reused today. We show that this reuse opens a supply-chain bac...
Gemini 3.8 Flash and 3.8 Flash Cyber deliver next-generation intelligence for agentic workflows and cybersecurity.
Google introduces Gemini 3.5 Flash Cyber, a lightweight cybersecurity model to find and patch vulnerabilities.
Students from the MIT Cybersecurity Clinic help local governments and other vulnerable organizations defend against digital threats.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
