Nanjing University is one of China’s top research institutions, known for academic rigor and research leadership in physics, chemistry, and AI. It plays a key role in China’s innovation strategy. NEC Labs America collaborates with Nanjing University on large language modeling, semantic search, and efficient attention mechanisms for NLP. Please read about our latest news and collaborative publications with Nanjing University.

Posts

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors

/in /by

The advent of large language models (LLMs) has revolutionized the field of text generation, producing outputs that closely mimic human-like writing. Although academic and industrial institutions have developed detectors to prevent the malicious usage of LLM-generated texts, other research has doubt about the robustness of these systems. To stress test these detectors, we introduce a humanized proxy-attack (HUMPA) strategy that effortlessly compromises LLMs, causing them to produce outputs that align with human-written text and mislead detection systems. Our method attacks the source model by leveraging a reinforcement learning (RL) fine-tuned humanized small language model (SLM) in the decoding phase. Through an in-depth analysis, we demonstrate that our attack strategy is capable of generating responses that are indistinguishable to detectors, preventing them from differentiating between machine-generated and human-written text. We conduct systematic evaluations on extensive datasets using proxy-attacked open-source models, including Llama2-13B, Llama3-70B, and Mixtral-8×7B in both white- and black-box settings. Our findings show that the proxy-attack strategy effectively deceives the leading detectors, resulting in an average AUROC drop of 70.4% across multiple datasets, with a maximum drop of 95.0% on a single dataset. Furthermore, in cross-discipline scenarios, our strategy also bypasses these detectors, leading to a significant relative decrease of up to 90.9%, while in cross-language scenario, the drop reaches 91.3%. Despite our proxy-attack strategy successfully bypassing the detectors with such significant relative drops, we find that the generation quality of the attacked models remains preserved, even within a modest utility budget, when compared to the text produced by the original, unattacked source model.

Read more

A Query System for Efficiently Investigating Complex Attack Behaviors for Enterprise Security

/in /by

The need for countering Advanced Persistent Threat (APT) attacks has led to the solutions that ubiquitously monitor system activities in each enterprise host, and perform timely attack investigation over the monitoring data for uncovering the attack sequence. However, existing general-purpose query systems lack explicit language constructs for expressing key properties of major attack behaviors, and their semantics-agnostic design often produces inefficient execution plans for queries. To address these limitations, we build Aiql, a novel query system that is designed with novel types of domain-specific optimizations to enable efficient attack investigation. Aiql provides (1) a domain-specific data model and storage for storing the massive system monitoring data, (2) a domain-specific query language, Attack Investigation Query Language (Aiql) that integrates critical primitives for expressing major attack behaviors, and (3) an optimized query engine based on the characteristics of the data and the semantics of the query to efficiently schedule the execution. We have deployed Aiql in NEC Labs America comprising 150 hosts. In our demo, we aim to show the complete usage scenario of Aiql by (1) performing an APT attack in a controlled environment, and (2) using Aiql to investigate such attack by querying the collected system monitoring data that contains the attack traces. The audience will have the option to perform the APT attack themselves under our guidance, and interact with the system and investigate the attack via issuing queries and checking the query results through our web UI.

Read more

AIQL: Enabling Efficient Attack Investigation from System Monitoring Data

/in /by

The need for countering Advanced Persistent Threat (APT) attacks has led to solutions that ubiquitously monitor system activities in each host and perform timely attack investigation over the monitoring data for analyzing attack provenance. However, existing query systems based on relational databases and graph databases lack language constructs to express key properties of major attack behaviors, and often execute queries inefficiently since their semantics-agnostic design cannot exploit the properties of system monitoring data to speed up query execution.To address this problem, we propose a novel query system built on top of existing monitoring tools and databases, which is designed with novel types of optimizations to support timely attack investigation. Our system provides (1) domain-specific data model and storage for scaling the storage, (2) a domain-specific query language, Attack Investigation Query Language (AIQL) that integrates critical primitives for attack investigation, and (3) an optimized query engine based on the characteristics of the data and the semantics of the queries to efficiently schedule the query execution. We deployed our system in NEC Labs America comprising 150 hosts and evaluated it using 857 GB of real system monitoring data (containing 2.5 billion events). Our evaluations on a real-world APT attack and a broad set of attack behaviors show that our system surpasses existing systems in both efficiency (124x over PostgreSQL, 157x over Neo4j, and 16x over Greenplum) and conciseness (SQL, Neo4j Cypher, and Splunk SPL contain at least 2.4x more constraints than AIQL).

Read more