Large language models (LLMs) possess immense capabilities but are susceptible to malicious exploitation. To mitigate the risk, safety alignment is employed to align LLMs with ethical standards. However, safety-aligned LLMs may remain vulnerable to carefully crafted jailbreak attacks, but these attacks often face high rejection rates and limited harmfulness. In this paper, we expose the vulnerabilities of safety alignment in open-access LLMs, which can significantly enhance the success rate and harmfulness of jailbreak attacks. Through reverse alignment, achieved by accessing model parameters, we show the feasibility of efficiently fine-tuning LLMs to undermine their inherent safeguards. We investigate two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO). RSFT operates by supervising the fine-tuning of LLMs to reverse their inherent values. We also explore how to prepare data needed for RSFT. RPO optimizes LLMs to enhance their preference for harmful content, reversing the models’ safety alignment. Our extensive experiments reveal that open-access high-performance LLMs can be adeptly reverse-aligned to output harmful content, even in the absence of manually curated malicious datasets. Our research acts as a whistleblower for the community, emphasizing the need to pay more attention to safety of open-accessing LLMs. It also underscores the limitations of current safety alignment approaches and calls for research on robust safety alignment methods to counteract malicious fine-tuning attacks.

Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on these LLMs, which can benefit various natural language processing (NLP) tasks for customers. However, previous studies have shown that EaaS is vulnerable to model extraction attacks, which can cause significant losses for the owners of LLMs, as training these models is extremely expensive. To protect the copyright of LLMs for EaaS, we propose an Embedding Watermark method called {pasted macro ‘METHOD’} that implants backdoors on embeddings. Our method selects a group of moderate-frequency words from a general text corpus to form a trigger set, then selects a target embedding as the watermark, and inserts it into the embeddings of texts containing trigger words as the backdoor. The weight of insertion is proportional to the number of trigger words included in the text. This allows the watermark backdoor to be effectively transferred to EaaS-stealer’s model for copyright verification while minimizing the adverse impact on the original embeddings’ utility. Our extensive experiments on various datasets show that our method can effectively protect the copyright of EaaS models without compromising service quality. Our code is available at https://github.com/yjw1029/EmbMarker.

Query-aware webpage snippet extraction is widely used in search engines to help users better understand the content of the returned webpages before clicking. The extracted snippet is expected to summarize the webpage in the context of the input query. Existing snippet extraction methods mainly rely on handcrafted features of overlapping words, which cannot capture deep semantic relationships between the query and webpages. Another idea is to extract the sentences which are most relevant to queries as snippets with existing text matching methods. However, these methods ignore the contextual information of webpages, which may be sub-optimal. In this paper, we propose an effective query-aware webpage snippet extraction method named DeepQSE. In DeepQSE, the concatenation of title, query and each candidate sentence serves as an input of query-aware sentence encoder, aiming to capture the fine-grained relevance between the query and sentences. Then, these query-aware sentence representations are modeled jointly through a document-aware relevance encoder to capture contextual information of the webpage. Since the query and each sentence are jointly modeled in DeepQSE, its online inference may be slow. Thus, we further propose an efficient version of DeepQSE, named Efficient-DeepQSE, which can significantly improve the inference speed of DeepQSE without affecting its performance. The core idea of Efficient-DeepQSE is to decompose the query-aware snippet extraction task into two stages, i.e., a coarse-grained candidate sentence selection stage where sentence representations can be cached, and a fine-grained relevance modeling stage. Experiments on two datasets validate the effectiveness and efficiency of our methods.

News recommendation is a widely adopted technique to provide personalized news feeds for the user. Recently, pre-trained language models (PLMs) have demonstrated the great capability of natural language understanding and benefited news recommendation via improving news modeling. However, most existing works simply finetune the PLM with the news recommendation task, which may suffer from the known domain shift problem between the pre-training corpus and downstream news texts. Moreover, PLMs usually contain a large volume of parameters and have high computational overhead, which imposes a great burden on low-latency online services. In this paper, we propose Tiny-NewsRec, which can improve both the effectiveness and the efficiency of PLM-based news recommendation. We first design a self-supervised domain-specific post-training method to better adapt the general PLM to the news domain with a contrastive matching task between news titles and news bodies. We further propose a two-stage knowledge distillation method to improve the efficiency of the large PLM-based news recommendation model while maintaining its performance. Multiple teacher models originated from different time steps of our post-training procedure are used to transfer comprehensive knowledge to the student model in both its post-training stage and finetuning stage. Extensive experiments on two real-world datasets validate the effectiveness and efficiency of our method.

News recommendation is critical for personalized news access. Most existing news recommendation methods rely on centralized storage of users’ historical news click behavior data, which may lead to privacy concerns and hazards. Federated Learning is a privacy-preserving framework for multiple clients to collaboratively train models without sharing their private data. However, the computation and communication cost of directly learning many existing news recommendation models in a federated way are unacceptable for user clients. In this paper, we propose an efficient federated learning framework for privacy-preserving news recommendation. Instead of training and communicating the whole model, we decompose the news recommendation model into a large news model maintained in the server and a light-weight user model shared on both server and clients, where news representations and user model are communicated between server and clients. More specifically, the clients request the user model and news representations from the server, and send their locally computed gradients to the server for aggregation. The server updates its global user model with the aggregated gradients, and further updates its news model to infer updated news representations. Since the local gradients may contain private information, we propose a secure aggregation method to aggregate gradients in a privacy-preserving way. Experiments on two real-world datasets show that our method can reduce the computation and communication cost on clients while keep promising model performance.