Related papers: When the Ruler is Broken: Parsing-Induced Suppress…

Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite…

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

LLMs reliably correct false claims when presented in isolation, yet when the same claims are embedded in task-oriented requests, they often comply rather than correct. We term this failure mode \emph{correction suppression} and construct a…

Software systems generate massive, evolving, semi-structured logs that are central to reliability engineering and AIOps, yet difficult to analyze at scale under drift and limited labels. Recent advances in pretrained Transformer models and…

LLM agents do not act on raw interaction history; they act on a bounded decision state assembled by truncation, summarization, reordering, and rewriting. If directive-bearing state is dropped, weakened, or rebound during that step, an agent…

The integration of large language models (LLMs) into enterprise systems has introduced a new class of covert security vulnerabilities, particularly within logic execution layers and persistent memory contexts. This paper introduces…

The advent of instruction-tuned Large Language Models designed for coding tasks (Code LLMs) has transformed software engineering practices. However, their robustness against various input challenges remains a critical concern. This study…

Security analysts routinely query system logs to detect threats and investigate incidents, but each log source uses its own semi-structured format: logs are cheap to produce, but expensive to use. The standard approach, building per-source…

Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications. We uncover a…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods…

We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic investigation from alert parroting. Derived from 129 anonymized incident patterns with…

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused…

Batch prompting, which combines a batch of multiple queries sharing the same context in one inference, has emerged as a promising solution to reduce inference costs. However, our study reveals a significant security vulnerability in batch…

Trustworthy evaluations of dangerous capabilities are increasingly crucial for determining whether an AI system is safe to deploy. One empirically demonstrated threat is sandbagging - the strategic underperformance on evaluations by AI…

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt…

Large Language Models (LLM) continue to demonstrate their utility in a variety of emergent capabilities in different fields. An area that could benefit from effective language understanding in cybersecurity is the analysis of log files.…

The rapid proliferation of Large Language Models (LLMs) has heightened concerns regarding their exposure to jailbreak attacks, which craft adversarial inputs designed to elicit unsafe content. Although proprietary models such as GPT-4 have…

Large Language Model-based systems (LLM systems) are information and query processing systems that use LLMs to plan operations from natural-language prompts and feed the output of each successive step into the LLM to plan the next. This…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…