Related papers: Prompt Injection Detection is Regime-Dependent: A …

Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This study systematically evaluates five leading LALMs across…

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK…

Semantic parsing, i.e., the automatic derivation of meaning representation such as an instantiated predicate-argument structure for a sentence, plays a critical role in deep processing of natural language. Unlike all other top systems of…

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

Social networks are frequently polluted by rumors, which can be detected by advanced models such as graph neural networks. However, the models are vulnerable to attacks and understanding the vulnerabilities is critical to rumor detection in…

Prompt injection has emerged as a critical vulnerability in large language model (LLM) deployments, yet existing research is heavily weighted toward defenses. The attack side -- specifically, which injection strategies are most effective…

We propose a novel Reinforcement Learning model for discrete environments, which is inherently interpretable and supports the discovery of deep subgoal hierarchies. In the model, an agent learns information about environment in the form of…

Machine Learning systems are increasingly deployed in decision-making settings that shape user behavior and, in turn, the data on which future decisions are based. Performative Prediction (PP) formalizes this feedback loop by modeling how…

Prior work uses linear probes on benchmark prompts as evidence of evaluation awareness in large language models. Because evaluation context is typically entangled with benchmark format and genre, it is unclear whether probe-based signals…

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…

Intrusion Detection is an invaluable part of computer networks defense. An important consideration is the fact that raising false alarms carries a significantly lower cost than not detecting at- tacks. For this reason, we examine how…

Large language models (LLMs) have exhibited remarkable capabilities across diverse open-domain tasks, yet their application in specialized domains such as civil engineering remains largely unexplored. This paper starts bridging this gap by…

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks can cause LLMs to…

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those…

Jailbreaking in Large Language Models (LLMs) threatens their safe use in sensitive domains like education by allowing users to bypass ethical safeguards. This study focuses on detecting jailbreaks in 2-Sigma, a clinical education platform…

Intelligent anomaly detection in dynamic visual environments requires reconciling real-time performance with semantic interpretability. Conventional approaches address only fragments of this challenge. Reconstruction-based models capture…

The design of safety-critical agents based on large language models (LLMs) requires more than simple prompt engineering. This paper presents a comprehensive information-theoretic analysis of how rule encodings in system prompts influence…

Prompt injection attacks represent a major vulnerability in Large Language Model (LLM) deployments, where malicious instructions embedded in user inputs can override system prompts and induce unintended behaviors. This paper presents a…

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current…

Vision-language foundation models (VLMs) show promise for diverse imaging tasks but often underperform on medical benchmarks. Prior efforts to improve performance include model finetuning, which requires large domain-specific datasets and…