45 articles mentioning security-slm-unsloth-1.5b
arXiv:2610.27152v1 Announce Type: cross Abstract: Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency and improved privacy compared to cloud-based deployment. However, on-device models embedded in mobile applications can be unpacked
arXiv:2610.27304v1 Announce Type: cross Abstract: Large language models are deployed globally, yet safety alignment and evaluation remain concentrated in English: harmful requests refused in English can elicit unsafe completions when translated into low-resource languages. We evaluate ten widely dep
arXiv:2606.08270v3 Announce Type: cross Abstract: University Academic Management Information Systems (ACMIS) are high-value targets for a wide spectrum of security threats including brute-force login attacks, payment fraud, privilege escalation, insider data theft, and academic integrity violations.
arXiv:2609.00445v3 Announce Type: replace-cross Abstract: Deployed language model safeguards (safety fine-tuning, filtering, unlearning) vary by principal only outside the model weights: filters are reconfigured, tiers are multiplied, and artefacts are reissued; inside one set of weights every reque
arXiv:2610.23449v1 Announce Type: new Abstract: AI agents have increasingly interacted with external environments by invoking tools, with Model Context Protocol (MCP) emerging as a standard interface for connecting agents to heterogeneous tools and services. As organizations deploy agents at scale,
arXiv:2610.23307v1 Announce Type: cross Abstract: Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: a
arXiv:2610.18566v2 Announce Type: replace Abstract: Large language model (LLM) routers reduce serving cost by choosing which model to call and how many output tokens to grant it for each query. Existing routers rank model-budget actions using a single quality metric. This does not work for mixed wor
arXiv:2610.23685v1 Announce Type: cross Abstract: Implementing Security Technical Implementation Guide (STIG) controls remains a demanding operating-system administration task. Each natural-language security requirement must be translated into a precise and persistent configuration change. These cha
arXiv:2610.21565v2 Announce Type: replace-cross Abstract: On-device deployment of large language models (LLMs) is increasingly adopted due to latency and privacy requirements, but exposes proprietary models to reverse engineering and intellectual property theft. Trusted Execution Environments (TEEs)
arXiv:2609.19705v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents already trade with real capital, yet agent-security research has mostly treated them as generic agents. Trading changes the threat: a compromised agent's orders move prices that other participants act on, and
arXiv:2610.22244v1 Announce Type: cross Abstract: Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far. Users write those requests in many languages, while guard prompts and the benchmarks on which purpose-built gu
arXiv:2610.07657v2 Announce Type: replace Abstract: LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial content. Current defenses for MAS are typically evaluated in isolation, focusing on one attack type at a time, which can lead to cost
arXiv:2510.15476v4 Announce Type: replace-cross Abstract: Prompt-security claims for large language models (LLMs) are often compared as properties of individual attacks or defenses, although measured harmfulness depends on the target model, access setting, attack and defense configuration, prompt sa
arXiv:2610.18262v1 Announce Type: cross Abstract: Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such instructions in skill files for agents to decode and follow. We evaluate Caesar and layered variants
arXiv:2610.17020v1 Announce Type: cross Abstract: Cybersecurity evaluations of AI agents have focused largely on offense, yet a working exploit does not show that an agent can make software safe. An attacker needs to exploit only one vulnerability; a defender must find and fix all of them. We introd
arXiv:2610.15995v1 Announce Type: cross Abstract: This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Network (O-RAN) testing. Unlike approaches relying on static rule sets or privileged access to raw packe
arXiv:2610.15482v1 Announce Type: cross Abstract: Large Language Models accelerate software development but introduce severe security vulnerabilities. This systematic review investigates security risks in automated coding, benchmark limitations, and the role of human developers. Findings indicate th
arXiv:2610.03073v2 Announce Type: replace-cross Abstract: Security workflows need models that turn complex observations and explicit policies into decisions. System One models introduced by Jev return typed predictions and probabilities; security specialization supplies the domain expertise behind t
Block is building AI-powered security with OpenAI. Its security team investigates threats faster and proposes patches in minutes.
The problem with giving everyone in a company access to AI tools is that people will use them in unexpected ways. And that fact is steadily seeding fears that companies now have new, gaping security holes in their systems or, at least, will soon.
arXiv:2609.19844v2 Announce Type: replace-cross Abstract: AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable framework covering 31 tasks and 124 authored hardware-security regressions. A deterministic no
arXiv:2610.09892v2 Announce Type: replace-cross Abstract: Feedback from automated testing, human red teaming, and incident response can strengthen an AI system's defenses when discovered failures lead to effective repairs. We study when this feedback process provides sufficient protection and when i
arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents exploited research infrastructure, coordinated across runs, and compro
arXiv:2609.30805v2 Announce Type: replace-cross Abstract: Industrial control system attacks are usually documented in terms of the plant where they occurred: its sensors, actuators, process stages, and control logic. Yet many attacks express a more general physical pattern--such as suppressing flow,
arXiv:2609.34790v2 Announce Type: replace-cross Abstract: LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries may remain fixed or evolve with changes in membership, roles, composition, and relationships.
arXiv:2609.33401v2 Announce Type: replace-cross Abstract: Model-based judges support agent security by detecting prompt injections, assessing interaction risks, and screening harmful requests. System One models select from predefined answers and report probabilities that software can use to allow, b
arXiv:2609.36167v1 Announce Type: cross Abstract: Distributed Denial of Service attacks are a growing threat to network infrastructure, and new techniques, including the use of generative AI, make them harder to detect. Traditional detection systems, such as rule based firewalls, often fail to ident
The round builds on a $30 million fundraise in February, taking the company's total funding to $140 million.
arXiv:2509.22796v2 Announce Type: replace-cross Abstract: Open-source software projects are foundational to modern software ecosystems, with the Linux kernel standing out as a critical exemplar due to its ubiquity and complexity. Although security patches are continuously integrated into the Linux m
arXiv:2609.30345v2 Announce Type: cross Abstract: Cloud-security investigation is dominated by population tasks: which identities can read a data store, how many resources fail a control, what is reachable from another account. These resolve against a complete inventory, not a named object, so a par
arXiv:2609.28915v1 Announce Type: cross Abstract: LLM agents are deployed into infrastructure that grants them broad host authority, yet existing agent-security benchmarks and defenses operate almost exclusively at the application telemetry layer: the served tool manifest, the user prompt, and the m
arXiv:2609.27903v1 Announce Type: new Abstract: Due to the rapid development of information technology, a huge and complex traffic network has been established across various sectors, including aviation, aerospace, vehicles, ships, electric power, and industry. However, because of the complexity and
arXiv:2603.18740v4 Announce Type: replace-cross Abstract: 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
arXiv:2609.27202v1 Announce Type: cross Abstract: The growing deployment of Internet of Things (IoT) devices has increased the need for privacy-preserving intrusion detection systems that operate directly on resource-constrained hardware. Federated Learning enables collaborative model training witho
OpenAI CEO Sam Altman discusses AI safety, human control, and international cooperation in remarks to the United Nations Security Council.
arXiv:2609.23700v1 Announce Type: cross Abstract: Large language model agents are now privileged principals that take consequential actions: editing code repositories, operating inboxes, completing purchases. Their authority is kernel-grade, but it comes without what classical systems security requi
arXiv:2609.25352v1 Announce Type: cross Abstract: Evaluation of large language models (LLMs) for safety, security, and privacy (SSP) relies heavily on static benchmarks, which suffer from score saturation, data contamination, and aggregation artifacts, and fail to capture sensitivity to linguistic v
arXiv:2609.22792v1 Announce Type: cross Abstract: LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and patch generation. Improving them at the model level demands expert demonstrations or computable rewards, which security tasks rarely offer: traces
arXiv:2609.23894v1 Announce Type: cross Abstract: Agentic AI extends LLM security beyond generated content to persistent state, autonomous actions, tool use, and interactions with humans and other agents. Existing threat classifications often emphasize individual dimensions, obscuring connections am
arXiv:2609.24515v1 Announce Type: cross Abstract: AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for legal compliance, governance, accountability, and security; current fra
arXiv:2608.28021v2 Announce Type: replace-cross Abstract: Large language models increasingly author Infrastructure-as-Code (IaC), where one insecure default is provisioned straight into production. Prior evaluations report vulnerability counts for models only, and so cannot say whether models are wo
arXiv:2609.26598v1 Announce Type: cross Abstract: The future 6G networks are expected to incorporate a proliferation of wireless services in diverse environments, which presents a significant challenge for information security. Conventionally optimization always requires recalculation and learning s
arXiv:2609.24669v1 Announce Type: cross Abstract: Providing autonomous intelligence, pervasive connectivity and usability to human life and industry has led to the emergence of the Internet of Things (IoT). To support time-sensitive and resource-constrained applications, IoT systems nowadays increas
arXiv:2609.24662v1 Announce Type: new Abstract: LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume passive users and static control, ignoring the interactive dynamics that shape real agent behavior.
arXiv:2609.22724v1 Announce Type: cross Abstract: Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specific security policies. Existing trajectory-level defenses rely on LLM prompting or rigid rules, and thu