Related papers: Trust Me, Import This: Dependency Steering Attacks…

Jailbreak attacks on Language Model Models (LLMs) entail crafting prompts aimed at exploiting the models to generate malicious content. Existing jailbreak attacks can successfully deceive the LLMs, however they cannot deceive the human.…

Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to…

As large language models (LLMs) become integrated into sensitive workflows, concerns grow over their potential to leak confidential information. We propose TrojanStego, a novel threat model in which an adversary fine-tunes an LLM to embed…

Service system performance depends on how participants respond to design choices, but modeling these responses is hard due to the complexity of human behavior. We introduce an LLM-powered multi-agent simulation (LLM-MAS) framework for…

Open source code is considered a common practice in modern software development. However, reusing other code allows bad actors to access a wide developers' community, hence the products that rely on it. Those attacks are categorized as…

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…

Large Language Models (LLMs) are seeing significant adoption in every type of organization due to their exceptional generative capabilities. However, LLMs are found to be vulnerable to various adversarial attacks, particularly prompt…

LLM-based coding agents are increasingly used to generate code, tests, and documentation. Still, their outputs can be plausible yet misaligned with developer intent and provide limited evidence for review in evolving projects. This limits…

Generative models such as large language models are extensively used as code copilots and for whole program generation. However, the programs they generate often have questionable correctness, authenticity and reliability in terms of…

Hallucinations in large language models (LLMs) are outputs that are syntactically coherent but factually incorrect or contextually inconsistent. They are persistent obstacles in high-stakes industrial settings such as engineering design,…

Relying on dependency packages accelerates software development, but it also increases the exposure to security vulnerabilities that may be present in dependencies. While developers have full control over which dependency packages (and…

Hallucinations in large language models (LLMs) produce fluent continuations that are not supported by the prompt, especially under minimal contextual cues and ambiguity. We introduce Distributional Semantics Tracing (DST), a model-native…

Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks poorly understood. We present the first large-scale empirical study of this problem,…

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

Background. In modern software development, the use of external libraries and packages is increasingly prevalent, streamlining the software development process and enabling developers to deploy feature-rich systems with little coding. While…

Large language models (LLMs) hallucinate: they produce fluent outputs that are factually incorrect. We present a geometric dynamical systems framework in which hallucinations arise from task-dependent basin structure in latent space. Using…

We investigate a family of poisoning attacks against Support Vector Machines (SVM). Such attacks inject specially crafted training data that increases the SVM's test error. Central to the motivation for these attacks is the fact that most…

Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified…

Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…

Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external content observed…