Recent advances in diffusion models have enabled the creation of deceptively real images, posing significant security risks when misused. In this study, we empirically show that different timesteps of DDIM inversion reveal varying subtle distinctions between synthetic and real images that are extractable for detection, taking the forms of such as Fourier power spectrum high-frequency discrepancies and inter-pixel variance distributions. Based on these observations, we propose a novel detection method named ESIDE that directly utilizes features of intermediately noised images by training an ensemble on multiple noised timesteps, circumventing the overtime of conventional reconstruction-based strategies. To enhance human comprehension, we introduce a metric-grounded explanation refinement module to identify and explain AI-generated flaws. Additionally, we present the benchmarks GenHard and GenExplain, offering detection samples of greater difficulty and high-quality rationales for fake images. Extensive experiments show that ESIDE achieves state-of-the-art performance with 98.91% and 95.89% detection accuracy on regular and challenging samples respectively, and demonstrates generalizability and robustness.

Feiran Zhang, Yixin Wu, Zhenghua Wang, Xiaohua Wang, Changze Lv, Xuanjing Huang, Xiaoqing Zheng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has been limited research into the underlying mechanisms that make LLMs vulnerable to such attacks. In this study, we suggest that the self-safeguarding capability of LLMs is linked to specific activity patterns within their representation space. Although these patterns have little impact on the semantic content of the generated text, they play a crucial role in shaping LLM behavior under jailbreaking attacks. Our findings demonstrate that these patterns can be detected with just a few pairs of contrastive queries. Extensive experimentation shows that the robustness of LLMs against jailbreaking can be manipulated by weakening or strengthening these patterns. Further visual analysis provides additional evidence for our conclusions, providing new insights into the jailbreaking phenomenon. These findings highlight the importance of addressing the potential misuse of open-source LLMs within the community.

Backpropagation is the foundational algorithm for training neural networks and a key driver of deep learning’s success. However, its biological plausibility has been challenged due to three primary limitations: weight symmetry, reliance on global error signals, and the dual-phase nature of training, as highlighted by the existing literature. Although various alternative learning approaches have been proposed to address these issues, most either fail to satisfy all three criteria simultaneously or yield suboptimal results. Inspired by the dynamics and plasticity of pyramidal neurons, we propose Dendritic Localized Learning (DLL), a novel learning algorithm designed to overcome these challenges. Extensive empirical experiments demonstrate that DLL satisfies all three criteria of biological plausibility while achieving state-of-the-art performance among algorithms that meet these requirements. Furthermore, DLL exhibits strong generalization across a range of architectures, including MLPs, CNNs, and RNNs. These results, benchmarked against existing biologically plausible learning algorithms, offer valuable empirical insights for future research. We hope this study can inspire the development of new biologically plausible algorithms for training multilayer networks and advancing progress in both neuroscience and machine learning. Our code is available at https://github.com/Lvchangze/Dendritic-Localized-Learning.

Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

This article deals with the problem of detecting maritime targets embedded in nonhomogeneous sea clutter, where the limited number of secondary data is available due to the heterogeneity of sea clutter. A class of linear discriminant analysis (LDA)-based matrix information geometry (MIG) detectors is proposed in the supervised scenario. As customary, Hermitian positive-definite (HPD) matrices are used to model the observational sample data, and the clutter covariance matrix of the received dataset is estimated as the geometric mean of the secondary HPD matrices. Given a set of training HPD matrices with class labels, which are elements of a higher dimensional HPD matrix manifold, the LDA manifold projection learns a mapping from the higher dimensional HPD matrix manifold to a lower dimensional one subject to maximum discrimination. In this study, the LDA manifold projection, with the cost function maximizing between-class distance while minimizing within-class distance, is formulated as an optimization problem in the Stiefel manifold. Four robust LDA-MIG detectors corresponding to different geometric measures are proposed. Numerical results based on both simulated radar clutter with interferences and real IPIX radar data show the advantage of the proposed LDA-MIG detectors against their counterparts without using LDA and the state-of-the-art maritime target detection methods in nonhomogeneous sea clutter.

Many flow-related design optimization problems like aircraft and automobile aerodynamic design are solved via computational fluid dynamics (CFD) simulations. However, CFD simulations are known to be resource-demanding and time-consuming. Deep learning (DL) is emerging as a viable means to accelerate CFD simulations by directly predicting the outcomes of multiple simulation iterations. While promising, existing DL-based models have to be re-trained whenever the flow condition changes, which incurs significant training overhead for real-life scenarios with a wide range of flow conditions. This paper presents FLOWGAN, a novel conditional generative adversarial network for accurate prediction of flow fields in various conditions. FlowGAN is designed to directly obtain the generation of solutions to flow fields in various conditions based on observations rather than re-training. As FlowGAN does not rely on knowledge of the underlying governing equations, it can quickly adapt to various flow conditions and avoid the need for expensive re-training. We evaluate FlowGAN by applying it to scenarios of simulating both the whole flow field and selected regions of interest (RoI). Compared to the state-of-the-art DL based methods, FlowGAN significantly reduces the prediction errors by 2.27% while exhibiting a better generalization ability.

This paper studies the performance characteristics of computational fluid dynamics (CFD) applications on Intel Many Integrated Core (MIC) architecture. Three CFD applications, BT-MZ, LM3D and HOSTA, are evaluated on Intel Knights Corner (KNC) coprocessor, the first public MIC product. The results show that the pure OpenMP scalability of these applications is not sufficient to utilize the potential of a KNC coprocessor. While utilizing the hybrid MPI/OpenMP programming model helps to improve the parallel scalability, the maximum parallel speedup relative to a single thread is still not satisfactory. The OpenCL version of BT-MZ performs better than the OpenMP version but is not comparable to the MPI version and the hybrid MPI/OpenMP version. At the micro-architecture level, while the three CFD applications achieve reasonable instruction execution rates and L1 data cache hit rates, use a large percent of vector instructions, they have low arithmetic density, incur very high branch misprediction rates and do not utilize the Vector Processing Unit efficiently. As a result, they achieve very low single thread floating-point efficiency. For these applications to attain competitive performance on the MIC architecture as on the Xeon processors, both the parallel scalability and the single thread performance should be improved, which is a difficult task.

Memory wall is an important factor that influences program performance, and its alleviation relies on memory optimization of the program. Static approaches optimize memory performance based on analytical models that are hard to achieve because of increasing architecture complexity and code structures. Execution-driven approaches like iterative compilation achieve it by executing different versions of the program on actual platforms and select the one that renders best performance, outperforming static compilation approaches significantly. But the expensive compilation cost has limited their application scope to embedded applications and a small group of math kernels. This paper proposes a different approach-Combining Model and Iterative Compilation for Effective Memory Optimization (MICEMemO). Such an approach first constructs a memory optimization model based on hardware performance counters to decide how and when to apply transformations, and then selects the optimal transformation parameters using genetic algorithms. Experimental results show that our performance counter based approach can greatly reduce programs' memory access time and influence ratio for memory reference, improve programs' memory performance, therefore, effectively alleviate the problem of memory wall.

The performance gap for high performance applications has been widening over time. High level program transformations are critical to improve the applications' performance, many of which concern the determination of optimal values for transformation parameters, such as loop unrolling and blocking. Traditional compilers select these parameters based on static analytical models. However, complex computer architectures and code behaviors greatly limit the strength of optimizing compilers. Iterative compilation approach determines these parameter values by executing the program with different parameter values and selects the one with the shortest runtime, outperforming static compilation approaches significantly, which makes it a hot research topic in the high performance computing research community. But itpsilas quite time consuming because of the huge optimization space. Therefore, an effective search strategy is crucial for iterative compilation. This paper investigates the Nelder-Mead simplex algorithm for iterative compilation optimization parameter search. Experimental results indicate Nelder-Mead simplex based search strategy can produce parameter values with better performance and lower cost.

Imagine stream processor has shown high performance and efficiency for media applications. Its potential for scientific applications is of great interest to the high performance computing community. This paper investigates this subject from a new angle. It roughly classifies the scientific programs into three classes based on their computation to memory access ratios. For each class, typical programs are programmed with StreamC/KernelC stream language and simulated based on the cycle-accurate simulator of Imagine. In-depth analysis is carried out for the performance data, with special attentions on the performance bottlenecks. The performance data obtained on Imagine are compared against data on two general-purpose x86 processors. The results show that programs with no DRAM accesses attain high floating point performance and efficiencies on Imagine. These programs' performance is only restricted by limited ILP (Instruction-Level Parallelism) and load imbalance across ALUs. Programs with computation to memory operation ratios O(n) attain absolute floating point performance on Imagine comparable to that obtained on general-purpose processors, but their floating-point efficiencies are not satisfactory. It is essential to optimize these programs for high SRF (Stream Register File) and LRF (Local Register File) reuse and high ILP on Imagine. Programs with lower computation to memory operation ratios attain much lower floating-point performance and efficiencies on Imagine, compared to those obtained on x86 processors.

Since comparative sequence analysis is effective for non-coding RNA detection and RNA secondary structure prediction, efficient computational methods are expected for structuraf alignment of RNA sequences. However, it is very difficuit to construct a weft structuraf afignment without knowing the secondary structures. In this paper, we present a new method for constructing structural alignment of RNA sequences by detecting and assessing conserved stems. The method can be summarized by: 1) we detect conserved stems across multiple RNA sequences using the so-called position matrix with which some common paired positions are uncovered; 2) we assess the conserved stems using the Signal-to-Noise; 3) we build the structural alignment by incorporating some compatible conserved stems with the initial sequence alignment constructed by Clustal W program. We tested our method on the data sets composed of known structural alignments taken from the Rfam database. Experimentai resufts show that our method can buifd structuraf afignment of RNA sequences with much greater sensitivity and specificity than Clustal W.