BPBiswabandan Panda

Biswabandan Panda

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Biswabandan Panda has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Differential Privacy for Secure Cache Partitioning: Promises, Limits, and Fixes

    by Prerna Priyadarshini, Abhijat Bharadwaj, Biswabandan Panda

    The shared last-level cache (LLC) enables cross-core contention-based attacks. While LLC randomization mitigates conflict-based attacks, cache partitioning prevents all attack classes. Recent secure partitioning techniques dynamically allocate LLC space and claim security against cache occupancy attacks. We show that state-of-the-art LLC usage-based dynamic partitioning remains vulnerable. Focusing on Secure and Scalable Cache Partitioning (SCALE), which applies differential privacy-based noise to LLC way allocations, we demonstrate that allocations can be denoised over time to construct a reliable LLC occupancy channel. The key insight that drives the occupancy channel is that differential privacy protects individual allocations; it does not hide long-term statistics such as the mean, median, and standard deviation. We showcase a novel LLC occupancy attack that does application fingerprint exploiting statistical properties. Finally, we propose lightweight fixes that mitigate this leakage.

  • Open Access

    ICARUS: Criticality and Reuse based Instruction Caching for Datacenter Applications

    by Vedant Kalbande, Hrishikesh Jedhe Deshmukh, Alberto Ros, Biswabandan Panda


  • Untangling the Low Accuracy of the Entangling Instruction Prefetcher

    by Vedant Kalbande, Biswabandan Panda, Alexandra Jimborean, Alberto Ros

    The Entangling Instruction Prefetcher (EIP) is a state-of-the-art mechanism designed to improve instruction-fetch timeliness. While earlier studies report an average prefetch accuracy of 72% and as high as 91%, more recent evaluations using different methodologies—most notably the gem5 simulator— report lower accuracies of 44% on average and even below 30%. This work aims to shed light on this controversy by providing a robust and faithful open-source implementation within the gem5 simulation framework. In addition, we analyze several design choices that influence EIP's accuracy and performance highlighting common pitfalls when porting EIP across simulators. In our experiments, using the same benchmarks as prior studies, our gem5 version of EIP achieves an average prefetch accuracy of 64.35%, demonstrating that its accuracy remains stable across the simulators.

  • Open Access

    The Avatar Cache: Enabling On-Demand Security with Morphable Cache Architecture

    by Anubhav Bhatla, Navneet Navneet, Moinuddin Qureshi, Biswabandan Panda

    The sharing of the last-level cache (LLC) among multiple cores makes it vulnerable to cross-core conflict- and occupancy-based attacks. Despite extensive prior work, modern processors still employ non-secure set-associative LLCs. Existing secure LLC designs broadly fall into two categories: (i) randomized and (ii) partitioned. The state-of-the-art randomized design, Mirage, mitigates conflict-based attacks but incurs significant area overhead (20% additional storage) and design complexity. Partitioned LLCs mitigate both conflict- and occupancy-based attacks, but often suffer from large performance overheads (on average over 5% and up to 49%), require OS support in set-based schemes, or face scalability issues in way-based schemes. These factors pose major obstacles to the industrial adoption of secure LLCs. This paper asks whether strong LLC security can be achieved with minimal changes to a conventional set-associative LLC, enabling security only when needed while preserving low performance, power, and area overheads. We propose Avatar, a secure and morphable LLC that supports three modes: non-secure (Avatar-N), randomized secure (Avatar-R), and partitioned secure (Avatar-P), and can switch dynamically between them. Avatar closely resembles a conventional set-associative LLC, facilitating industrial adoption. Avatar-R introduces extra invalid entries and leverages high associativity to provide a strong security guarantee with little capacity loss, achieving only one set-associative eviction per $10^{30}$ years, while incurring 1.5% storage overhead, a 2.7% increase in static power, and a 0.2% slowdown over a 16~MB baseline. Avatar-P mitigates both conflict- and occupancy-based attacks with only a 3% performance overhead, substantially outperforming prior way-based partitioned LLCs. When security is unnecessary, Avatar switches to Avatar-N to maximize performance and energy efficiency.

  • Open Access

    A Complexity-Effective Local Delta Prefetcher

    by Agustín Navarro-Torres, Biswabandan Panda, Jesús Alastruey-Benedé, Pablo Ibáñez, Víctor Viñnals-Yúfera, Alberto Ros

    Data prefetching is crucial for performance in modern processors by effectively masking long-latency memory accesses. Over the past decades, numerous data prefetching mechanisms have been proposed, which have continuously reduced the access latency to the memory hierarchy. Several state-of-the-art prefetchers, namely Instruction Pointer Classifier Prefetcher (IPCP) and Berti, target the first-level data cache, and thus, they are able to completely hide the miss latency for timely prefetched cache lines. Berti exploits timely local deltas to achieve high accuracy and performance. This paper extends Berti with a larger evaluation and with extra optimizations on top of the previous conference paper. The result is a complexity-effective version of Berti that outperforms it for a large amount of workloads and simplifies its control logic. The key for those advancements is a simple mechanism for learning timely deltas without the need to track the fetch latency of each cache miss. Our experiments conducted with a wide range of workloads (CVP traces by Qualcomm, SPEC CPU2017, and GAP) show performance improvements by 4.0% over a mainstream stride prefetcher, and by a non-negligible 1.4% over the previously published version of Berti requiring similar storage.


  • SPAM: Streamlined Prefetcher-Aware Multi-Threaded Cache Covert-Channel Attack

    by E. Kritheesh, Biswabandan Panda

    Last-level cache (LLC) covert-channels exploit the cache timing differences to transmit information. In recent works, the attacks rely on a single sender and a single receiver. Streamline is the state-of-the-art cache covert channel attack that uses a shared array of addresses mapped to the payload bits, allowing parallelization of the encoding and decoding of bits. As multi-core systems are ubiquitous, multiple senders and receivers can be used to create a high bandwidth cache covert channel. However, this is not the case, and the bandwidth per thread is limited by various factors. We extend Streamline to a multi-threaded Streamline, where the senders buffer a few thousand bits at the LLC for the receivers to decode. We observe that these buffered bits are prone to eviction by the co-running processes before they are decoded. We propose SPAM, a multi-threaded covert-channel at the LLC. SPAM shows that fewer but faster senders must encode for more receivers to reduce this time frame. This ensures resilience to noise coming from cache activities of co-running applications. SPAM uses two different access patterns for the sender(s) and the receiver(s). The sender access pattern of the addresses is modified to leverage the hardware prefetchers to accelerate the loads while encoding. The receiver access pattern circumvents the hardware prefetchers for accurate load latency measurements. We demonstrate SPAM on a six-core (12-threaded) system, achieving a bit-rate of 12.21 MB/s at an error rate of 9.02% which is an improvement of over 70% over the state-of-the-art multi-threaded Streamline for comparable error rates when 50% of the co-running threads stress the cache system.


  • The Game of Latency, Bandwidth, and Hardware Prefetching

    by Biswabandan Panda

    A processor’s cache hierarchy exploits locality in memory accesses to reduce latency but can’t satisfy all memory accesses. Modern processors contain hardware prefetchers to predict data to be used in the future and bring them into a cache in a timely manner.


  • Open Access

    CLIP: Load Criticality based Data Prefetching for Bandwidth-constrained Many-core Systems

    by Biswabandan Panda

    Hardware prefetching is a latency-hiding technique that hides the costly off-chip DRAM accesses. However, state-of-the-art prefetchers fail to deliver performance improvement in the case of many-core systems with constrained DRAM bandwidth. For SPEC CPU2017 homogeneous workloads, the state-of-the-art Berti L1 prefetcher, on a 64-core system with four and eight DRAM channels, incurs performance slowdowns of 24% and 16%, respectively. However, Berti improves performance by 35% if we use an unrealistic configuration of 64 DRAM channels for a 64-core system (one DRAM channel per core). Prior approaches such as prefetch throttling and critical load prefetching are not effective in the presence of state-of-the-art prefetchers. Existing load criticality predictors fail to detect loads that are critical in the presence of hardware prefetching and the best predictor provides an average critical load prediction accuracy of 41%. Existing prefetch throttling techniques use prefetch accuracy as one of the primary metrics. However, these techniques offer limited benefits for state-of-the-art prefetchers that deliver high prefetch accuracy and use prefetcher-specific throttling and filtering. We propose CLIP, a novel load criticality predictor for hardware prefetching with constrained DRAM bandwidth. Our load criticality predictor provides an average accuracy of more than 93% and as high as 100%. CLIP also filters out the critical loads that lead to accurate prefetching. For a 64-core system with eight DRAM channels, CLIP improves the effectiveness of state-of-the-art Berti prefetcher by 24% and 9% for 45 and 200 64-core homogeneous and heterogeneous workload mixes, respectively. We show that CLIP is equally effective in the presence of other state-of-the-art L1 and L2 prefetchers. Overall, CLIP incurs a storage overhead of 1.56KB/core.


  • Open Access

    InviSeal: A Stealthy Dynamic Analysis Framework for Android Systems

    by Saurabh Kumar, Debadatta Mishra, Biswabandan Panda, Sandeep Kumar Shukla

    With wide adaptation of open-source Android into mobile devices by different device vendors, sophisticated malware are developed to exploit security vulnerabilities. As comprehensive security analysis on physical devices are impractical and costly, emulator driven security analysis has gained popularity in recent times. Existing dynamic analysis frameworks suffer from two major issues: (i) they do not provide foolproof anti-emulation-detection measures even for fingerprint-based attacks, and (ii) lack efficient cross-layer profiling capabilities. In this work, we present InviSeal, a comprehensive and scalable dynamic analysis framework that includes low-overhead cross-layer profiling techniques and detailed anti-emulation-detection measures along with the basic emulation features. While providing an emulator-based comprehensive analysis platform, InviSeal strives to remain behind-the-scene to avoid emulation-detection. We empirically demonstrate that the proposed OS layer profiling utility to achieve cross-layer profiling is ∼ 1.26X faster than existing strace-based approaches. Overall, on average, InviSeal incurs ∼ 1.04X profiling overhead in terms of the number of operations performed by the various workloads of the CaffeineMark-3.0 benchmark, which is better than the contemporary techniques. Furthermore, we measure the anti-emulation-detection strategies of InviSeal against the fingerprint-based emulation-detection attacks. Experimental results show that the emulation-detection attacks carried out by the malware samples do not find InviSeal as an emulated platform.