40 articles mentioning Jack-3.8-27B-Coder-16GB-VRAM
arXiv:2607.19957v2 Announce Type: replace-cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs). Traditional prefix-based reuse has low cache hit rates across inference requests because it requires exact token and position matches. To improve efficiency, rece
Buzz is a group chat platform for the workplace that puts humans and their AI agents in the same conversation.
arXiv:2602.10382v3 Announce Type: replace Abstract: Backdoor attacks pose significant security risks for Large Language Models (LLMs), yet the internal mechanisms by which triggers operate remain poorly understood. We present the first mechanistic analysis of trigger-induced language-switching backd
arXiv:2511.20002v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibility of hijacking multip
arXiv:2506.18756v2 Announce Type: replace Abstract: LLMs increasingly integrate auto-suggestion optimization modules, enabling them to rewrite and display user input before generating the final response. While this design aims to enhance transparency and trust, its process of autonomously selecting
arXiv:2606.11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution. We identify and
arXiv:2606.11017v1 Announce Type: new Abstract: Airport surface operations increasingly constrain performance at high-throughput hubs. This study examines arrival taxi-in decisions at Hartsfield-Jackson Atlanta International Airport (KATL) and proposes a two-stage, data-driven decision aid that mirr
arXiv:2606.10371v1 Announce Type: cross Abstract: Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomotor policies vulnerable to adversarial manipulation. Most prior attacks focus on disruption: they per
arXiv:2605.30292v2 Announce Type: replace-cross Abstract: Conformal prediction methods enjoy strong theoretical and empirical predictive inference performance, provided the data is exchangeable and is treated symmetrically during training. However, these assumptions are impractical in many settings,
arXiv:2603.23117v2 Announce Type: cross Abstract: By integrating Chain-of-Thought (CoT) reasoning, Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, particularly by improving generalization and interpretability. However, the security of CoT-based reas
Meta's AI support chatbot helped hackers hijack Instagram accounts, as reported earlier by 404 Media. In a video shared on Telegram, a hacker shows how they could take over an account by asking Meta's chatbot to switch the email associated with someone else's profile and then reset the password. The
arXiv:2605.29960v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this capability also introduces a new attack surface: memory poisoning, where adversaries can inject malicious info
arXiv:2605.28632v1 Announce Type: cross Abstract: Cryptographic watermarking is a leading defense for attributing text generated by large language models (LLMs). Existing schemes, including KGW, Unigram, and DipMark, derive their security guarantees from the assumption that the underlying pseudo-ran
arXiv:2605.28074v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially crafted yet flue
arXiv:2605.28112v1 Announce Type: cross Abstract: Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because raw data remain local. As a result, routing must rely on client-provided semantic profiles, creating a new opportunity for manipulation. We int
arXiv:2605.26154v1 Announce Type: cross Abstract: LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks primarily man
arXiv:2510.26418v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reasoning should lead to more robust safety behavior, we find evidence to the contrary: over-extended re
arXiv:2605.25707v1 Announce Type: new Abstract: Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups, resolution chan
arXiv:2605.22756v1 Announce Type: new Abstract: Random forests are widely used in fields involving sensitive tabular data, but existing approaches to enforcing differential privacy (DP) typically degrade performance to the point of impracticality. In this paper, we introduce Lumberjack, a differenti
arXiv:2605.17310v1 Announce Type: cross Abstract: Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries. This pape
Yesterday, in Musk v. Altman, before the jurors came in, Sam Altman's team passed up what looked - from a distance - like a Little League trophy. It was not. Judge Yvonne Gonzalez Rogers had the lawyers read the inscription aloud for the press: "Never stop being a jackass." It's a commemoration Open
arXiv:2605.13115v1 Announce Type: cross Abstract: Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor attack that hijacks the PRNG to deterministically control generated images. A malicious PRNG, injected v
arXiv:2605.12673v1 Announce Type: new Abstract: Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges spontaneously in fron
arXiv:2605.08313v1 Announce Type: cross Abstract: Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chain attack surface overlooked by existing defenses. We present SeedHijack, a backdoor attack that mani
arXiv:2605.08310v1 Announce Type: cross Abstract: Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject malicious instruct
arXiv:2605.07273v1 Announce Type: cross Abstract: Multimodal RAG systems increasingly rely on vision-language retrievers to ground visual queries in external textual evidence. Existing adversarial studies on RAG mainly manipulate the retrieval corpus or memory, while attacks on vision-language and r
arXiv:2604.10271v3 Announce Type: replace-cross Abstract: In what way could a data breach involving government-issued IDs such as passports, driver's licenses, etc., rival a random voluntary disclosure on a nondescript social-media platform? At first glance, the former appears more significant, and
arXiv:2605.02946v1 Announce Type: cross Abstract: Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly adopted to scale model capacity, understanding their safety robustness becomes essential. Existing
arXiv:2602.07249v2 Announce Type: replace-cross Abstract: Autonomous Vehicles (AVs), especially vision-based AVs, are rapidly being deployed without human operators. As AVs operate in safety-critical environments, understanding their robustness in an adversarial environment is an important research
arXiv:2505.16888v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed via third-party system prompts downloaded from public marketplaces. We identify a critical supply-chain vulnerability: conditional system prompt poisoning, where an adversary injects a ``
arXiv:2604.20994v1 Announce Type: cross Abstract: The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by invoking external functions. Injection and jailbreaking attacks have been
arXiv:2604.17375v1 Announce Type: cross Abstract: Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning temporal, action, object, and spatial understanding. However, we identify a critical yet overlooked i
arXiv:2505.10846v3 Announce Type: replace Abstract: This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in large reasoning models (LRMs). At its core, AutoRAN pioneers an execution simulation paradigm that leverages a weaker but less-aligned model
arXiv:2604.13049v1 Announce Type: cross Abstract: Online reviews and recommendation systems help users navigate overwhelming choice, but they are vulnerable to self-reinforcing distortions. This paper examines how a single malicious reviewer can exploit popularity-biased rating dynamics and whether
arXiv:2604.05549v2 Announce Type: replace Abstract: With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may impact th
arXiv:2604.09651v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like $\pi_0$ showing great promise in generating smooth, continuous actions. As these models advance, their unique action generation mechanism
arXiv:2604.10299v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer from slow
arXiv:2604.09470v1 Announce Type: new Abstract: Translating natural language into Jira Query Language (JQL) requires resolving ambiguous field references, instance-specific categorical values, and complex Boolean predicates. Single-pass LLMs cannot discover which categorical values (e.g., component
arXiv:2604.00076v2 Announce Type: cross Abstract: Reinforcement Learning (RL) agents often struggle with efficiency and performance in complex environments. We propose a novel framework that uses a Large Language Model (LLM) to dynamically generate a curriculum over available actions, enabling the a